https://aclanthology.org/2023.findings-acl.373/
Xinnan Guo, Wentao Deng, Yongrui Chen, Yang Li, Mengdi Zhou, Guilin Qi, Tianxing Wu, Dong Yang, Liubin Wang, Yong Pan. Findings of the Association for...
contrastivepretrainingmultiscale
https://deepai.org/publication/sort-ing-vqa-models-contrastive-gradient-learning-for-improved-consistency
10/20/20 - Recent research in Visual Question Answering (VQA) has revealed state-of-the-art models to be inconsistent in their understanding ...
sortingvqamodelscontrastive
https://github.com/StupidBuluchacha/UrbanCLIP
Learning Text-Enhanced Urban Region Profiling with Contrastive Language-Image Pre-Training - StupidBuluchacha/UrbanCLIP
urban regiongithublearningtextenhanced
https://elie.net/talk/facade-high-precision-insider-threat-detection-using-contrastive-learning
This talk presents FACADE, a novel self-supervised AI system used by Google to detect insider threats with high precision. FACADE uses a contrastive learning...
high precisioninsider threatcontrastive learningfacadedetection
https://imbue.com/research/2020-08-24-appendix-for-understanding-self-supervised-contrastive-learning/
The BYOL terminology is used throughout this blog post. To compare to other papers, see the below table. Name SimCLR MoCo BYOL (used…
contrastive learningappendixquotunderstandingself
https://arxiv.org/abs/2505.08194
Abstract page for arXiv paper 2505.08194: CLTP: Contrastive Language-Tactile Pre-training for 3D Contact Geometry Understanding
contrastivelanguagetactilepretraining
https://deepai.org/publication/simplifying-open-set-video-domain-adaptation-with-contrastive-learning
01/09/23 - In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed tha...
open setdomain adaptationcontrastive learningsimplifyingvideo
https://openreview.net/forum?id=uvTea5Rfek&referrer=%5Bthe%20profile%20of%20Scott%20Linderman%5D(%2Fprofile%3Fid%3D~Scott_Linderman1)
Recent work indicates that low-dimensional dynamics of neural and behavioral data are often preserved across days and subjects. However, extracting these...
extractingtaskrelevantpreserveddynamics
https://arxiv.org/abs/2311.12075v3
Abstract page for arXiv paper 2311.12075v3: BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
attack ondualembeddingguidedbackdoor
https://deepai.org/publication/selective-supervised-contrastive-learning-with-noisy-labels
03/08/22 - Deep networks have strong capacities of embedding data into latent representations and finishing following tasks. However, the cap...
contrastive learningselectivesupervisednoisylabels
https://openreview.net/forum?id=BYBanbBubV&referrer=%5Bthe%20profile%20of%20Kwot%20Sin%20Lee%5D(%2Fprofile%3Fid%3D~Kwot_Sin_Lee1)
While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we...
image generationinfomaxganimprovedadversarial
https://openreview.net/forum?id=36uvYtrYL7&referrer=%5Bthe%20profile%20of%20Xiaolin%20Zheng%5D(%2Fprofile%3Fid%3D~Xiaolin_Zheng1)
Large language models (LLMs) have demonstrated impressive performance in text generation tasks; however, their embedding spaces often suffer from the isotropy...
multi levelfine tuningcontrastiveterminologyadaptation
https://xiangyuxu0815.github.io/tags/contrastive-loss/
The highly-customizable Hugo Academic theme powered by Hugo Blox Builder. Easily create your personal academic website.
contrastive lossxuwebsite
https://deepai.org/publication/robust-robotic-control-from-pixels-using-contrastive-recurrent-state-space-models
12/02/21 - Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. Howev...
robotic controlstate spacerobustpixelsusing
https://openreview.net/forum?id=-5_B8g3CcSr&referrer=%5Bthe%20profile%20of%20Xinyu%20Li%5D(%2Fprofile%3Fid%3D~Xinyu_Li4)
Existing contrastive learning methods sample intra-video positives and we incorporate inter-video nearest-neighbors to improve performance on a variety of...
contrastive learninglookgloballylocallyinter
https://nielseniq.com/global/en/info/block-scl-blocking-matters-for-supervised-contrastive-learning-in-product-matching/
Block SCL revolutionizes product matching with supervised contrastive learning, boosting accuracy and efficiency. Learn more
contrastive learningblocksclproductmatching
https://j-min.io/publication/crg_eccv2024/
Jan 28, 2025 - CRG is a training-free method that guides VLMs to help understand the visual prompts, by contrasting the outputs with & without visual prompts. - *[ECCV...
language modelscontrastiveregionguidanceimproving
https://openreview.net/forum?id=08IgHjpk4z7&referrer=%5Bthe%20profile%20of%20Sarthak%20Bhagat%5D(%2Fprofile%3Fid%3D~Sarthak_Bhagat1)
Retrieving facial images from attributes plays a vital role in various systems such as face recognition and suspect identification. Compared to other image...
image retrievalfacialusingcontrastivepersonalization
https://openreview.net/forum?id=hiciJQdmpw&referrer=%5Bthe%20profile%20of%20Haowei%20Lin%5D(%2Fprofile%3Fid%3D~Haowei_Lin1)
Deep generative models have achieved substantial success in protein design. A prevalent approach for de novo protein design involves initially designing a...
dualflowscontrastiveguidancegenerating
https://openreview.net/forum?id=Clr1z6sIKP&referrer=%5Bthe%20profile%20of%20Rasmus%20H%C3%B8ier%5D(%2Fprofile%3Fid%3D~Rasmus_H%C3%B8ier1)
Activity difference based learning algorithms---such as contrastive Hebbian learning and equilibrium propagation---have been proposed as biologically plausible...
contrastive hebbian learningdualpropagationacceleratingdyadic
https://deepai.org/publication/contrastive-learning-for-fair-representations
09/22/21 - Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal pre...
contrastive learningfairrepresentations
https://openreview.net/forum?id=l9vM_PaUKz&referrer=%5Bthe%20profile%20of%20Zhan%20Tong%5D(%2Fprofile%3Fid%3D~Zhan_Tong1)
We leverage the soft neighbors to sufficiently explore the correlation information among samples in cotrastive learning.
visual representationsoftneighborspositivesupporters