self supervised - Robuta Search

https://aclanthology.org/2020.findings-emnlp.419/ Guiding Attention for Self-Supervised Learning with Transformers - ACL Anthology Ameet Deshpande, Karthik Narasimhan. Findings of the Association for Computational Linguistics: EMNLP 2020. 2020. self supervised learning guiding attention transformers acl https://www.amazon.science/publications/self-supervised-pretraining-for-large-scale-point-clouds Self-supervised pretraining for large-scale point clouds - Amazon Science Pretraining on large unlabeled datasets has been proven to improve the down stream task performance on many computer vision tasks, such as 2D object detection... self supervised large scale point clouds pretraining amazon https://openreview.net/forum?id=nhtkdCvVLIh Self-Supervised Time Series Representation Learning with Temporal-Instance Similarity Distillation... We propose a self-supervised methods for pre-training universal time series representations using similarity distillation. self supervised time series representation learning https://deepai.org/publication/self-supervised-3d-human-pose-estimation-with-multiple-view-geometry Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry | DeepAI Aug 17, 2021 - 08/17/21 - We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera sy... 3d human pose estimation self supervised https://wandb.ai/byyoung3/ML_NEWS/reports/Self-Supervised-Image-Recognition-with-IJEPA---Vmlldzo4NDk5MzM1 Self-Supervised Image Recognition with IJEPA self supervised image recognition ijepa https://openreview.net/forum?id=4opFXRtBp1&referrer=%5Bthe%20profile%20of%20Zhenhua%20Wang%5D(%2Fprofile%3Fid%3D~Zhenhua_Wang5) Self-Supervised Enhancement for Named Entity Disambiguation via Multimodal Graph Convolution |... Named entity disambiguation (NED) finds the specific meaning of an entity mention in a particular context and links it to a target entity. With the emergence... named entity disambiguation self supervised enhancement https://arxiv.org/html/2503.13940v1 Multi-Modal Self-Supervised Semantic Communication multi modal self supervised semantic communication https://deepai.org/publication/self-supervised-depth-learning-for-urban-scene-understanding Self-Supervised Depth Learning for Urban Scene Understanding | DeepAI Dec 13, 2017 - 12/13/17 - As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It ... self supervised urban scene depth learning understanding https://deepai.org/publication/online-self-supervised-scene-segmentation-for-micro-aerial-vehicles Online Self-supervised Scene Segmentation for Micro Aerial Vehicles | DeepAI Jun 13, 2018 - 06/13/18 - Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles ... micro aerial vehicles self supervised online scene segmentation https://www.ibm.com/think/topics/self-supervised-learning What Is Self-Supervised Learning? | IBM Self-supervised learning is a machine learning technique that uses unsupervised learning for tasks typical to supervised learning, without labeled data. self supervised learning ibm https://aclanthology.org/2025.xllm-1.18/ Cognitive Mirroring for DocRE: A Self-Supervised Iterative Reflection Framework with... Xu Han, Bo Wang, Yueheng Sun, Dongming Zhao, Zongfeng Qu, Ruifang He, Yuexian Hou, Qinghua Hu. Proceedings of the 1st Joint Workshop on Large Language Models... self supervised cognitive mirroring https://arxiv.org/abs/2003.07905v1 [2003.07905v1] Self-Supervised Log Parsing Abstract page for arXiv paper 2003.07905v1: Self-Supervised Log Parsing self supervised 2003 log parsing https://deepai.org/publication/mt4ssl-boosting-self-supervised-speech-representation-learning-by-integrating-multiple-targets MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets |... Nov 14, 2022 - 11/14/22 - In this paper, we provide a new perspective on self-supervised speech models from how the self-training targets are obtained. We g... self supervised representation learning boosting speech https://deepai.org/publication/self-supervised-representation-learning-from-12-lead-ecg-data Self-supervised representation learning from 12-lead ECG data | DeepAI Mar 23, 2021 - 03/23/21 - We put forward a comprehensive assessment of self-supervised representation learning from short segments of clinical 12-lead elect... 12 lead ecg self supervised representation learning data deepai https://openreview.net/forum?id=1_jFneF07YC&referrer=%5Bthe%20profile%20of%20Matth%C3%A4us%20Kleindessner%5D(%2Fprofile%3Fid%3D~Matth%C3%A4us_Kleindessner2) Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations | OpenReview Strong and simple baseline for unsupervised segmentation methods obtained by leveraging and combining object-centric priors. semantic segmentation self supervised unsupervised object centric https://openreview.net/forum?id=xYJn2e1uu8 Sparsh: Self-supervised touch representations for vision-based tactile sensing | OpenReview In this work, we introduce general purpose touch representations for the increasingly accessible class of vision-based tactile sensors. Such sensors have led... self supervised tactile sensing sparsh touch representations https://openreview.net/forum?id=y0PQVjMbRf In-Context Symmetries: Self-Supervised Learning through Contextual World Models | OpenReview At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data... self supervised learning world models context symmetries https://research.google/blog/self-supervised-learning-advances-medical-image-classification/ Self-Supervised Learning Advances Medical Image Classification Posted by Shekoofeh Azizi, AI Resident, Google Research In recent years, there has been increasing interest in applying deep learning to medical im... self supervised learning medical image advances classification https://wandb.ai/mostafaibrahim17/ml-articles/reports/Breaking-Down-Self-Supervised-Learning-Concepts-Comparisons-and-Examples--Vmlldzo2MzgwNjIx Breaking Down Self-Supervised Learning: Concepts, Comparisons, and Examples Jan 5, 2024 - This article explores self-supervised learning in AI, discussing its methods, benefits, applications in various sectors, and the challenges it faces, while... self supervised learning breaking down concepts comparisons examples https://openreview.net/forum?id=HP7Qpui5YE Understanding Self-Supervised Pretraining with Part-Aware Representation Learning | OpenReview In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised methods learn part-aware... understanding self representation learning supervised pretraining part https://openreview.net/forum?id=h57gkDO2Yg Self-Supervised Dataset Distillation for Transfer Learning | OpenReview Dataset distillation aims to optimize a small set so that a model trained on the set achieves performance similar to that of a model trained on the full... self supervised transfer learning dataset distillation openreview https://openreview.net/forum?id=YmqAnY0CMEy Mathematical Reasoning via Self-supervised Skip-tree Training | OpenReview We demonstrate that self-supervised language modeling applied to mathematical formulas enables logical reasoning. To measure the logical reasoning abilities of... mathematical reasoning self supervised via skip tree https://openreview.net/forum?id=nVwJse40s1 Graph Adversarial Self-Supervised Learning | OpenReview This paper studies a long-standing problem of learning the representations of a whole graph without human supervision. The recent self-supervised learning... self supervised learning graph adversarial openreview https://arxiv.org/abs/1910.04076v1 [1910.04076v1] FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular... Abstract page for arXiv paper 1910.04076v1: FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous... self supervised 1910 https://oecd.ai/en/catalogue/metric-use-cases/self-supervised-video-representation-learning-with-cross-stream-prototypical-contrasting Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting - OECD.AI Online social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every... self supervised representation learning https://openreview.net/forum?id=AHm3dbp7D1D SEED: Self-supervised Distillation For Visual Representation | OpenReview This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used... self supervised visual representation seed distillation openreview https://openreview.net/forum?id=8DSUG_TnDCW&referrer=%5Bthe%20profile%20of%20Yufei%20He%5D(%2Fprofile%3Fid%3D~Yufei_He1) GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner | OpenReview Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label... self supervised decoding enhanced masked graph https://openreview.net/forum?id=9jXS07TIBH Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning | OpenReview We introduce a novel Pseudo-Negative Regularization (PNR) framework for effective continual self-supervised learning (CSSL). Our PNR leverages pseudo-negatives... self supervised learning pseudo negatives continual openreview https://deepai.org/publication/dsformer-a-dual-domain-self-supervised-transformer-for-accelerated-multi-contrast-mri-reconstruction DSFormer: A Dual-domain Self-supervised Transformer for Accelerated Multi-contrast MRI... Jan 26, 2022 - 01/26/22 - Multi-contrast MRI (MC-MRI) captures multiple complementary imaging modalities to aid in radiological decision-making. Given the n... self supervised https://arxiv.org/abs/2202.10360v1 [2202.10360v1] Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography... Abstract page for arXiv paper 2202.10360v1: Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography self supervised bulk motion https://openreview.net/forum?id=lAN7mytwrIy ElasticMVS: Learning elastic part representation for self-supervised multi-view stereopsis |... Self-supervised multi-view stereopsis (MVS) attracts increasing attention for learning dense surface predictions from only a set of images without onerous... self supervised multi view learning elastic part https://openreview.net/forum?id=xppLmXCbOw1 Self-supervised Visual Reinforcement Learning with Object-centric Representations | OpenReview Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a... self supervised reinforcement learning visual object centric https://openreview.net/forum?id=mjyMGFL8N2 Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss | OpenReview We propose a novel theoretical framework for studying self-supervised learning algorithms. self supervised deep learning https://openreview.net/forum?id=yEfmhgwslQ Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency | OpenReview Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions... time series self supervised model behavior encoding explanations https://openreview.net/forum?id=v5gjXpmR8J SSD: A Unified Framework for Self-Supervised Outlier Detection | OpenReview We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples... unified framework self supervised outlier detection ssd openreview https://openreview.net/forum?id=TRKwzPnXWQ ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning | OpenReview self supervised representation learning autoregressive pretraining video https://openreview.net/forum?id=Fy9bZ85xiX&referrer=%5Bthe%20profile%20of%20Yongsen%20Zheng%5D(%2Fprofile%3Fid%3D~Yongsen_Zheng1) Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for... The Matthew effect is a big challenge in Recommender Systems (RSs), where popular items tend to receive increasing attention, while less popular ones are often... self supervised learning matthew effect mitigating multi hypergraph https://www.marketresearchfuture.com/reports/france-self-supervised-learning-market-65050 France Self Supervised Learning Market Industry Growth | 2035 France Self Supervised Learning Market is Estimated to Grow a Valuation of USD 10,470.90 Million by 2035, Reaching at a CAGR of 33.82% During 2025 - 2035 self supervised learning industry growth france market 2035 https://openreview.net/forum?id=nJt27NQffr Self-Supervised Learning via Maximum Entropy Coding | OpenReview A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks,... self supervised learning maximum entropy via coding openreview https://openreview.net/forum?id=dPqfgsYn6l&referrer=%5Bthe%20profile%20of%20Arthur%20Aubret%5D(%2Fprofile%3Fid%3D~Arthur_Aubret1) Active Gaze Behavior Boosts Self-Supervised Object Learning | OpenReview Toddlers learn to recognize objects from different viewpoints with almost no supervision. Recent works argue that toddlers develop this ability by mapping... self supervised object learning active gaze behavior https://openreview.net/forum?id=BgjLy3chju&referrer=%5Bthe%20profile%20of%20Junru%20Zhang%5D(%2Fprofile%3Fid%3D~Junru_Zhang1) Multi-view Self-Supervised Contrastive Learning for Multivariate Time Series | OpenReview Learning semantic-rich representations from unlabeled time series data with intricate dynamics is a notable challenge. Traditional contrastive learning... multivariate time series self supervised contrastive learning view https://arxiv.org/abs/2510.02329 [2510.02329] SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification Abstract page for arXiv paper 2510.02329: SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification speculative decoding self supervised faster https://arxiv.org/abs/2509.19401 [2509.19401] SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs Abstract page for arXiv paper 2509.19401: SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs self supervised learning https://arxiv.org/abs/1907.11879 [1907.11879] Multi-task Self-Supervised Learning for Human Activity Detection Abstract page for arXiv paper 1907.11879: Multi-task Self-Supervised Learning for Human Activity Detection self supervised learning multi task for human 1907 https://openreview.net/forum?id=i1JDHqVzmv Self-Supervised Collaborative Distillation: Enhancing Lighting Robustness and 3D Awareness |... As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for... self supervised collaborative distillation enhancing lighting https://arxiv.org/abs/2204.02958 [2204.02958] LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature... Abstract page for arXiv paper 2204.02958: LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity self supervised https://deepai.org/publication/unfused-unsupervised-finetuning-using-self-supervised-distillation UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation | DeepAI Mar 10, 2023 - 03/10/23 - In this paper, we introduce UnFuSeD, a novel approach to leverage self-supervised learning and reduce the need for large amounts o... self supervised unsupervised finetuning using distillation https://arxiv.org/abs/2306.00689 [2306.00689] Stuttering Detection Using Speaker Representations and Self-supervised Contextual... Abstract page for arXiv paper 2306.00689: Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings self supervised 2306 stuttering detection using https://deepai.org/publication/self-supervised-iterative-contextual-smoothing-for-efficient-adversarial-defense-against-gray-and-black-box-attack Self-Supervised Iterative Contextual Smoothing for Efficient Adversarial Defense against Gray- and... Jun 22, 2021 - 06/22/21 - We propose a novel and effective input transformation based adversarial defense method against gray- and black-box attack, which i... self supervised https://arxiv.org/abs/2511.16674 [2511.16674] Dataset Distillation for Pre-Trained Self-Supervised Vision Models Abstract page for arXiv paper 2511.16674: Dataset Distillation for Pre-Trained Self-Supervised Vision Models self supervised dataset distillation https://www.amazon.science/publications/self-supervised-incremental-learning-of-object-representations-from-arbitrary-image-sets Self-supervised incremental learning of object representations from arbitrary image sets - Amazon... Computing a comprehensive and robust visual representation of an arbitrary object or category of objects is a complex problem. The difficulty increases when... self supervised incremental learning https://aclanthology.org/2020.coling-main.261/ Autoregressive Affective Language Forecasting: A Self-Supervised Task - ACL Anthology Matthew Matero, H. Andrew Schwartz. Proceedings of the 28th International Conference on Computational Linguistics. 2020. self supervised autoregressive affective language forecasting https://deepai.org/publication/catching-out-of-context-misinformation-with-self-supervised-learning Catching Out-of-Context Misinformation with Self-supervised Learning | DeepAI Jan 15, 2021 - 01/15/21 - Despite the recent attention to DeepFakes and other forms of image manipulations, one of the most prevalent ways to mislead audien... out of context self supervised learning catching misinformation deepai https://www.techtarget.com/healthtechanalytics/news/366589994/Self-supervised-foundation-models-mitigate-bias-in-histopathology-AI Self-supervised foundation models mitigate bias in histopathology AI | TechTarget Image classification models perform more accurately in white patients than in Black patients, but foundation models may help close these health equity gaps. self supervised foundation models mitigate bias histopathology https://openreview.net/forum?id=Tg2EVad7VF DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation |... Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages... self supervised normalization non autoregressive speech https://openreview.net/forum?id=gLOjNadTuj&referrer=%5Bthe%20profile%20of%20Yan%20Huang%5D(%2Fprofile%3Fid%3D~Yan_Huang2) Self-Supervised Recovery and Guide for Low-Resolution Person Re-Identification | OpenReview Low-resolution person re-identification is a challenging task to match low-resolution (LR) probes with high-resolution (HR) gallery images. To address the... self supervised https://openreview.net/forum?id=2wrQLJtygh Registration Quality Evaluation Metric with Self-Supervised Siamese Networks | OpenReview Registration is one of the most preliminary steps in many medical imaging downstream tasks. The registration quality determines the quality of the downstream... quality evaluation self supervised siamese networks registration metric https://www.marketresearchfuture.com/reports/japan-self-supervised-learning-market-65049 Japan Self Supervised Learning Market Industry Report | 2035 Japan Self Supervised Learning Market is Expected to Reach a Valuation of USD 18,337.99 Million by 2035, Growing at a CAGR of 33.81% During 2025 - 2035 self supervised learning industry report japan market 2035 https://www.mdpi.com/2072-4292/13/9/1673 Self-Supervised Monocular Depth Learning in Low-Texture Areas For the task of monocular depth estimation, self-supervised learning supervises training by calculating the pixel difference between the target image and the... self supervised monocular depth learning low https://arxiv.org/html/2602.08167v1 Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning self supervised bootstrapping action predictive embodied https://openreview.net/forum?id=o_V-MjyyGV_ Self-Supervised Policy Adaptation during Deployment | OpenReview In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different... self supervised policy adaptation deployment openreview https://openreview.net/forum?id=PXNrncg2DF SOHES: Self-supervised Open-world Hierarchical Entity Segmentation | OpenReview Open-world entity segmentation, as an emerging computer vision task, aims at segmenting entities in images without being restricted by pre-defined classes,... self supervised open world hierarchical entity segmentation https://openreview.net/forum?id=yLpuruMZHE Understanding the Role of Equivariance in Self-supervised Learning | OpenReview Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful... the role of self supervised learning understanding equivariance openreview https://deepai.org/publication/self-supervised-nuclei-segmentation-in-histopathological-images-using-attention Self-Supervised Nuclei Segmentation in Histopathological Images Using Attention | DeepAI Jul 16, 2020 - 07/16/20 - Segmentation and accurate localization of nuclei in histopathological images is a very challenging problem, with most existing app... self supervised using attention nuclei segmentation histopathological https://openreview.net/forum?id=9-umxtNPx5E Masked Frequency Modeling for Self-Supervised Visual Pre-Training | OpenReview We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly... self supervised pre training masked frequency modeling https://deepai.org/publication/dual-domain-self-supervised-learning-for-accelerated-non-cartesian-mri-reconstruction Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction | DeepAI Feb 18, 2023 - 02/18/23 - While enabling accelerated acquisition and improved reconstruction accuracy, current deep MRI reconstruction networks are typicall... self supervised learning https://openreview.net/forum?id=rylwJxrYDS vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations | OpenReview Learn how to quantize speech signal and apply algorithms requiring discrete inputs to audio data such as BERT. self supervised learning vq discrete speech representations https://openreview.net/forum?id=anQDiQZhDP Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement | OpenReview The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods... zero shot self supervised vevo controllable voice https://www.mcgill.ca/ece/category/tags/self-supervised-learning self-supervised learning | Electrical and Computer Engineering - McGill University self supervised learning electrical and computer engineering mcgill university https://openreview.net/forum?id=TJUfbYKo2c Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard... This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the... self supervised vision transformers https://openreview.net/forum?id=M5j42PvY65V Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning | OpenReview We improve momentum contrastive self-supervised learning for medical imaging datasets by having additional loss terms that brings the intermediate layer... self supervised learning intermediate layers matter momentum https://arxiv.org/abs/2507.21606v1 [2507.21606v1] Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking Abstract page for arXiv paper 2507.21606v1: Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking self supervised decoupled spatio temporal https://elifesciences.org/reviewed-preprints/99848v1/reviews CellSeg3D: self-supervised 3D cell segmentation for microscopy self supervised cell segmentation 3d microscopy https://deepai.org/publication/continual-wav2vec2-an-application-of-continual-learning-for-self-supervised-automatic-speech-recognition Continual-wav2vec2: an Application of Continual Learning for Self-Supervised Automatic Speech... Jul 26, 2021 - 07/26/21 - We present a method for continual learning of speech representations for multiple languages using self-supervised learning (SSL) a... an application self supervised continual https://github.com/facebookresearch/ssvp_slt GitHub - facebookresearch/ssvp_slt: Self-supervised video pretraining for sign language... Self-supervised video pretraining for sign language translation. - facebookresearch/ssvp_slt self supervised github facebookresearch ssvp slt https://arxiv.org/abs/1905.05375 [1905.05375] Self-supervised Audio Spatialization with Correspondence Classifier Abstract page for arXiv paper 1905.05375: Self-supervised Audio Spatialization with Correspondence Classifier self supervised audio spatialization 1905 correspondence classifier https://arxiv.org/abs/2006.03952 [2006.03952] Self-Supervised Dynamic Networks for Covariate Shift Robustness Abstract page for arXiv paper 2006.03952: Self-Supervised Dynamic Networks for Covariate Shift Robustness self supervised dynamic networks 2006 covariate shift https://openreview.net/forum?id=7DyKKOU6HR&referrer=%5Bthe%20profile%20of%20Hongxin%20Xiang%5D(%2Fprofile%3Fid%3D~Hongxin_Xiang2) Self-supervised Blending Structural Context of Visual Molecules for Robust Drug Interaction... Identifying drug-drug interactions (DDIs) is critical for ensuring drug safety and advancing drug development, a topic that has garnered significant research... self supervised https://openreview.net/forum?id=21MAX9LZ0P&referrer=%5Bthe%20profile%20of%20Yashas%20Malur%20Saidutta%5D(%2Fprofile%3Fid%3D~Yashas_Malur_Saidutta1) Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement |... Deep learning based speech enhancement (SE) approaches could suffer from performance degradation due to mismatch between training and testing environments. A... self supervised domain adaptation leveraging speech representations https://openreview.net/forum?id=Skx82ySYPH Neural Outlier Rejection for Self-Supervised Keypoint Learning | OpenReview Learning to extract distinguishable keypoints from a proxy task, outlier rejection. self supervised neural outlier rejection keypoint https://arxiv.org/abs/2206.12738 [2206.12738] Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes Abstract page for arXiv paper 2206.12738: Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes self supervised https://arxiv.org/abs/2308.05697 [2308.05697] SSLRec: A Self-Supervised Learning Framework for Recommendation Abstract page for arXiv paper 2308.05697: SSLRec: A Self-Supervised Learning Framework for Recommendation self supervised learning 2308 framework recommendation https://openreview.net/forum?id=gx3LMRB15C T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data | OpenReview Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples.... self supervised learning tabular data jepa augmentation free https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1109786/full Frontiers | Medical image segmentation based on self-supervised hybrid fusion network Automatic segmentation of medical images has been a hot research topic in the field of deep learning in recent years, and achieving accurate segmentation of ... medical image segmentation self supervised hybrid fusion frontiers based https://openreview.net/forum?id=CL-sVR9pvF Weighted Ensemble Self-Supervised Learning | OpenReview We efficiently ensemble SSL methods and train them with new objectives to get SOTA results on ImageNet-1K SSL evaluations. self supervised learning weighted ensemble openreview https://deepai.org/publication/self-supervised-video-representation-learning-by-video-incoherence-detection Self-Supervised Video Representation Learning by Video Incoherence Detection | DeepAI Sep 26, 2021 - 09/26/21 - This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It ro... self supervised representation learning video incoherence detection https://openreview.net/forum?id=LY6qkvd71Td Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized... To our knowledge, we are among the first to look into the fine-tuning of contrastive self-supervised models, which is an important yet under-explored question.... unleashing the power self supervised https://openreview.net/forum?id=ZbkqhKbggH ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks | OpenReview Existing self-supervised adversarial training (self-AT) methods rely on hand-crafted adversarial attack strategies for PGD attacks, which fail to adapt to the... self supervised astra adversarial training adaptive https://aclanthology.org/2024.findings-acl.931/ emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation - ACL Anthology Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, ShiLiang Zhang, Xie Chen. Findings of the Association for Computational Linguistics: ACL 2024.... self supervised pre training https://openreview.net/forum?id=fVu3o-YUGQK Efficient Self-supervised Vision Transformers for Representation Learning | OpenReview This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show... self supervised vision transformers representation learning efficient openreview https://arxiv.org/abs/2404.12386 [2404.12386] SOHES: Self-supervised Open-world Hierarchical Entity Segmentation Abstract page for arXiv paper 2404.12386: SOHES: Self-supervised Open-world Hierarchical Entity Segmentation self supervised open world 2404 hierarchical entity https://arxiv.org/abs/2309.10511 [2309.10511] Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising Abstract page for arXiv paper 2309.10511: Self2Seg: Single-Image Self-Supervised Joint Segmentation and Denoising single image self supervised 2309 https://fungi.ashita.nl/ No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations Self-supervised gradients enhance embeddings of pretrained models and achieve significant improvements in k-nearest neighbor classification and in-context... self supervised deep frozen train gain https://openreview.net/forum?id=iLo7Qj6Pfx MutEmbed: Self-Supervised Learning of Biological Latent Embeddings from Cancer Mutational Profiles... Cancer genomes possess diverse mutational patterns across multiple profiles, including single base substitutions (SBS), small insertions and deletions (ID),... self supervised learning https://www.amazon.science/publications/multilingual-knowledge-graph-completion-with-self-supervised-adaptive-graph-alignment Multilingual knowledge graph completion with self-supervised adaptive graph alignment - Amazon... Predicting missing facts in a knowledge graph (KG) is crucial as modern KGs are far from complete. Due to labor-intensive human labeling, this phenomenon... knowledge graph self supervised multilingual completion adaptive https://openreview.net/forum?id=DxciLhF085c&referrer=%5Bthe%20profile%20of%20Chenyuan%20Qu%5D(%2Fprofile%3Fid%3D~Chenyuan_Qu1) Multi-view Self-supervised Disentanglement for General Image Denoising | OpenReview With its significant performance improvements, the deep learning paradigm has become a standard tool for modern image denoisers. While promising performance... multi view self supervised for general image denoising disentanglement https://deepai.org/publication/self-supervised-learning-to-bring-dual-reversed-rolling-shutter-images-alive Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive | DeepAI May 31, 2023 - 05/31/23 - Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row... self supervised learning https://market.us/report/self-supervised-learning-market/ Self-Supervised Learning Market Size Share | CAGR at 36.10% Mar 13, 2026 - Self-Supervised Learning Market projected to grow significantly to about USD 353.4 billion by 2035, registering a CAGR of 36.10%. self supervised learning market size share cagr 36 https://research.google/blog/simper-simple-self-supervised-learning-of-periodic-targets/ SimPer: Simple self-supervised learning of periodic targets Posted by Daniel McDuff, Staff Research Scientist, and Yuzhe Yang, Student Researcher, Google Learning from periodic data (signals that repeat, suc... self supervised learning simper simple periodic targets https://deepai.org/publication/self-supervised-visual-lidar-odometry-with-flip-consistency Self-supervised Visual-LiDAR Odometry with Flip Consistency | DeepAI Jan 5, 2021 - 01/05/21 - Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and te... self supervised visual lidar odometry flip