An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning

• URL: http://arxiv.org/abs/2501.03507v1
• Date: Tue, 07 Jan 2025 03:50:11 GMT
• Title: An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning
• Authors: Fatemeh Ghofrani, Pooyan Jamshidi,
• Abstract summary: Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist.<n>We revisit the robust EMP-SSL framework, emphasizing the importance of increasing the number of crops per image to accelerate learning.<n>We extend this approach with free adversarial training in Multi-Crop SSL, introducing the Cost-Free Adversarial Multi-Crop Self-Supervised Learning (CF-AMC-SSL)
• Score: 1.590683264892176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods require extensive epochs to achieve convergence, a demand further amplified in adversarial settings. To address this inefficiency, we revisit the robust EMP-SSL framework, emphasizing the importance of increasing the number of crops per image to accelerate learning. Unlike traditional contrastive learning, robust EMP-SSL leverages multi-crop sampling, integrates an invariance term and regularization, and reduces training epochs, enhancing time efficiency. Evaluated with both standard linear classifiers and multi-patch embedding aggregation, robust EMP-SSL provides new insights into SSL evaluation strategies. Our results show that robust crop-based EMP-SSL not only accelerates convergence but also achieves a superior balance between clean accuracy and adversarial robustness, outperforming multi-crop embedding aggregation. Additionally, we extend this approach with free adversarial training in Multi-Crop SSL, introducing the Cost-Free Adversarial Multi-Crop Self-Supervised Learning (CF-AMC-SSL) method. CF-AMC-SSL demonstrates the effectiveness of free adversarial training in reducing training time while simultaneously improving clean accuracy and adversarial robustness. These findings underscore the potential of CF-AMC-SSL for practical SSL applications. Our code is publicly available at https://github.com/softsys4ai/CF-AMC-SSL.

Related papers

• Mixtraining: A Better Trade-Off Between Compute and Performance [19.187160313686782]
  MixTraining is a novel framework that interleaves several SSL and SL epochs within a unified mixtraining training phase. It enhances synergy between SSL and SL for improved accuracy and consolidates shared steps to reduce computation overhead. Experiments demonstrate that MixTraining offers a superior compute-performance trade-off compared to conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-26T19:25:27Z)
• SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training [68.7896349660824]
  We present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Alignment (S++) framework. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Alignment to align the disjoint classification layers in a post-hoc fashion.
  arXiv  Detail & Related papers  (2024-08-15T17:50:07Z)
• On the Discriminability of Self-Supervised Representation Learning [38.598160031349686]
  Self-supervised learning (SSL) has recently achieved significant success in downstream visual tasks. A notable gap still exists between SSL and supervised learning (SL), especially in complex downstream tasks.
  arXiv  Detail & Related papers  (2024-07-18T14:18:03Z)
• ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations [35.68752612346952]
  The need for abundant labelled data in supervised Adversarial Training (AT) has prompted the use of Self-Supervised Learning (SSL) techniques with AT. The direct application of existing SSL methods to adversarial training has been sub-optimal due to the increased training complexity of combining SSL with AT. We propose appropriate attack and defense losses at the feature and projector, alongside a combination of weak and strong augmentations for the teacher and student respectively.
  arXiv  Detail & Related papers  (2024-06-09T14:20:46Z)
• Reinforcement Learning-Guided Semi-Supervised Learning [20.599506122857328]
  We propose a novel Reinforcement Learning Guided SSL method, RLGSSL, that formulates SSL as a one-armed bandit problem. RLGSSL incorporates a carefully designed reward function that balances the use of labeled and unlabeled data to enhance generalization performance. We demonstrate the effectiveness of RLGSSL through extensive experiments on several benchmark datasets and show that our approach achieves consistent superior performance compared to state-of-the-art SSL methods.
  arXiv  Detail & Related papers  (2024-05-02T21:52:24Z)
• CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking [11.616031590118014]
  CroSSL allows for handling missing modalities and end-to-end cross-modal learning. We evaluate our method on a wide range of data, including motion sensors.
  arXiv  Detail & Related papers  (2023-07-31T17:10:10Z)
• Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness [69.39073806630583]
  Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. We propose a two-stage framework termed Decoupled Adversarial Contrastive Learning (DeACL)
  arXiv  Detail & Related papers  (2022-07-22T06:30:44Z)
• On Higher Adversarial Susceptibility of Contrastive Self-Supervised Learning [104.00264962878956]
  Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. It is still largely unknown if the nature of the representation induced by the two learning paradigms is similar. We identify the uniform distribution of data representation over a unit hypersphere in the CSL representation space as the key contributor to this phenomenon. We devise strategies that are simple, yet effective in improving model robustness with CSL training.
  arXiv  Detail & Related papers  (2022-07-22T03:49:50Z)
• Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning [60.26659373318915]
  Active learning (AL) and semi-supervised learning (SSL) are two effective, but often isolated, means to alleviate the data-hungry problem. We propose an innovative Inconsistency-based virtual aDvErial algorithm to further investigate SSL-AL's potential superiority. Two real-world case studies visualize the practical industrial value of applying and deploying the proposed data sampling algorithm.
  arXiv  Detail & Related papers  (2022-06-07T13:28:43Z)
• Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup [54.09898347820941]
  We propose textbfScenario-textbfAgnostic textbfMixup (SAMix) for both Self-supervised Learning (SSL) and supervised learning (SL) scenarios. Specifically, we hypothesize and verify the objective function of mixup generation as optimizing local smoothness between two mixed classes. A label-free generation sub-network is designed, which effectively provides non-trivial mixup samples and improves transferable abilities.
  arXiv  Detail & Related papers  (2021-11-30T14:49:59Z)
• Decoupled Contrastive Learning [23.25775900388382]
  We identify a noticeable negative-positive-coupling (NPC) effect in the widely used cross-entropy (InfoNCE) loss. By properly addressing the NPC effect, we reach a decoupled contrastive learning (DCL) objective function. Our approach achieves $66.9%$ ImageNet top-1 accuracy using batch size 256 within 200 epochs pre-training, outperforming its baseline SimCLR by $5.1%$.
  arXiv  Detail & Related papers  (2021-10-13T16:38:43Z)
• On Data-Augmentation and Consistency-Based Semi-Supervised Learning [77.57285768500225]
  Recently proposed consistency-based Semi-Supervised Learning (SSL) methods have advanced the state of the art in several SSL tasks. Despite these advances, the understanding of these methods is still relatively limited.
  arXiv  Detail & Related papers  (2021-01-18T10:12:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.