Robuta

https://openreview.net/forum?id=10hCbu70Sr Catastrophic overfitting can be induced with discriminative non-robust features | OpenReview Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast... be induced withrobust featurescatastrophicoverfitting https://www.naukri.com/code360/library/speeded-up-robust-features-surf Speeded Up Robust Features (SURF) - Naukri Code 360 In this article, we will see the basics of SURF and a brief about the feature extraction and description. speeded up robust featuressurfnaukricode360 https://openreview.net/forum?id=H1lZJpVFvr Robust Local Features for Improving the Generalization of Adversarial Training | OpenReview We propose a new stream of adversarial training approach called Robust Local Features for Adversarial Training (RLFAT) that significantly improves both the... local featuresadversarial trainingrobustimproving https://openreview.net/forum?id=lZgORA63ew Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs |... While adversarial fine-tuning can enhance the robustness of vision-language models (VLMs), such approaches are computationally expensive. Adversarial prompt... https://www.quicken.com/about-us/press/quicken-adds-robust-investment-tracking-to-simplifi/ Quicken adds robust investment tracking features to its personal finance app Simplifi | Quicken investment tracking https://arxiv.org/abs/2303.01052 [2303.01052] Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust... Abstract page for arXiv paper 2303.01052: Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial... https://arxiv.org/abs/2410.18083 [2410.18083] FIPER: Factorized Features for Robust Image Super-Resolution and Compression Abstract page for arXiv paper 2410.18083: FIPER: Factorized Features for Robust Image Super-Resolution and Compression image super resolution