paper-with-me

홈 › Papers

Using Multiple Self-Supervised Tasks Improves Model Robustness

2022-04-07 · Matthew Lawhon, Chengzhi Mao, Junfeng Yang

Deep networks achieve state-of-the-art performance on computer vision tasks, yet they fail under adversarial attacks that are imperceptible to humans. In this paper, we propose a novel defense that can dynamically adapt the input using the intrinsic structure from multiple self-supervised tasks. By simultaneously using many self-supervised tasks, our defense avoids over-fitting the adapted image to one specific self-supervised task and restores more intrinsic structure in the image compared to a single self-supervised task approach. Our approach further improves robustness and clean accuracy significantly compared to the state-of-the-art single task self-supervised defense. Our work is the first to connect multiple self-supervised tasks to robustness, and suggests that we can achieve better robustness with more intrinsic signal from visual data.

📄 PDF Abstract BibTeX arXiv:2204.03714

Code (1)

mattlawhon/selfsupdefense 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Self-Supervised Pretraining Improves Self-Supervised Pretraining

2021-03-23 · Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi 외

While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates…

Data AugmentationImage Augmentation

Improving out-of-distribution generalization via multi-task self-supervised pretraining

2020-03-30 · Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar 외

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are compara…

Adversarial RobustnessDomain GeneralizationFew-Shot LearningMulti-Task Learning+2

VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals

2026-05-13 · Yuxuan Weng, Wenhan Luo, Qijia Shao arxiv

Wearable devices enable continuous health monitoring from multimodal signals, but real-world deployment is hindered by limited labeled data and pervasive sensor incompleteness. While large-scale self-supervised pretraini…

Learning Background Invariance Improves Generalization and Robustness in Self-Supervised Learning on ImageNet and Beyond

2021-09-28 · NeurIPS Workshop ImageNet_PPF 2021 12 · Chaitanya Ryali, David J. Schwab, Ari S. Morcos

Recent progress in self-supervised learning has demonstrated promising results in multiple visual tasks. An important ingredient in high-performing self-supervised methods is the use of data augmentation by training mode…

Data AugmentationSaliency DetectionSelf-Supervised LearningUnsupervised Saliency Detection

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks

2024-07-17 · Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi, Yi Sui 외

Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been ex…

Adversarial RobustnessBenchmarkingDepth Estimationimage-classification+3