When Does Contrastive Learning Preserve Adversarial Robustness from
Pretraining to Finetuning?
- URL: http://arxiv.org/abs/2111.01124v1
- Date: Mon, 1 Nov 2021 17:59:43 GMT
- Title: When Does Contrastive Learning Preserve Adversarial Robustness from
Pretraining to Finetuning?
- Authors: Lijie Fan, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Chuang Gan
- Abstract summary: We propose AdvCL, a novel adversarial contrastive pretraining framework.
We show that AdvCL is able to enhance cross-task robustness transferability without loss of model accuracy and finetuning efficiency.
- Score: 99.4914671654374
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Contrastive learning (CL) can learn generalizable feature representations and
achieve the state-of-the-art performance of downstream tasks by finetuning a
linear classifier on top of it. However, as adversarial robustness becomes
vital in image classification, it remains unclear whether or not CL is able to
preserve robustness to downstream tasks. The main challenge is that in the
self-supervised pretraining + supervised finetuning paradigm, adversarial
robustness is easily forgotten due to a learning task mismatch from pretraining
to finetuning. We call such a challenge 'cross-task robustness
transferability'. To address the above problem, in this paper we revisit and
advance CL principles through the lens of robustness enhancement. We show that
(1) the design of contrastive views matters: High-frequency components of
images are beneficial to improving model robustness; (2) Augmenting CL with
pseudo-supervision stimulus (e.g., resorting to feature clustering) helps
preserve robustness without forgetting. Equipped with our new designs, we
propose AdvCL, a novel adversarial contrastive pretraining framework. We show
that AdvCL is able to enhance cross-task robustness transferability without
loss of model accuracy and finetuning efficiency. With a thorough experimental
study, we demonstrate that AdvCL outperforms the state-of-the-art
self-supervised robust learning methods across multiple datasets (CIFAR-10,
CIFAR-100, and STL-10) and finetuning schemes (linear evaluation and full model
finetuning).
Related papers
- Revisiting the Robust Generalization of Adversarial Prompt Tuning [4.033827046965844]
We propose an adaptive Consistency-guided Adrial Prompt Tuning (i.e., CAPT) framework to enhance the alignment of image and text features for adversarial examples.
We conduct experiments across 14 datasets and 4 data sparsity schemes to show the superiority of CAPT over other state-of-the-art adaption methods.
arXiv Detail & Related papers (2024-05-18T02:54:41Z) - FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision
Transformers [61.48709409150777]
Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks.
Existing large models tend to prioritize performance during training, potentially neglecting the robustness.
We develop a novel LNLoRA module, incorporating a learnable layer normalization before the conventional LoRA module.
We propose the FullLoRA-AT framework by integrating the learnable LNLoRA modules into all key components of ViT-based models.
arXiv Detail & Related papers (2024-01-03T14:08:39Z) - Initialization Matters for Adversarial Transfer Learning [61.89451332757625]
We discover the necessity of an adversarially robust pretrained model.
We propose Robust Linear Initialization (RoLI) for adversarial finetuning, which initializes the linear head with the weights obtained by adversarial linear probing.
Across five different image classification datasets, we demonstrate the effectiveness of RoLI and achieve new state-of-the-art results.
arXiv Detail & Related papers (2023-12-10T00:51:05Z) - The Importance of Robust Features in Mitigating Catastrophic Forgetting [0.7734726150561088]
We introduce the CL robust dataset and train four baseline models on both the standard and CL robust datasets.
Our results demonstrate that the CL models trained on the CL robust dataset experienced less catastrophic forgetting of the previously learned tasks than when trained on the standard dataset.
arXiv Detail & Related papers (2023-06-29T16:48:15Z) - Continual Learners are Incremental Model Generalizers [70.34479702177988]
This paper extensively studies the impact of Continual Learning (CL) models as pre-trainers.
We find that the transfer quality of the representation often increases gradually without noticeable degradation in fine-tuning performance.
We propose a new fine-tuning scheme, GLobal Attention Discretization (GLAD), that preserves rich task-generic representation during solving downstream tasks.
arXiv Detail & Related papers (2023-06-21T05:26:28Z) - Understanding Zero-Shot Adversarial Robustness for Large-Scale Models [31.295249927085475]
We identify and explore the problem of emphadapting large-scale models for zero-shot adversarial robustness.
We propose a text-guided contrastive adversarial training loss, which aligns the text embeddings and the adversarial visual features with contrastive learning.
Our approach significantly improves the zero-shot adversarial robustness over CLIP, seeing an average improvement of over 31 points over ImageNet and 15 zero-shot datasets.
arXiv Detail & Related papers (2022-12-14T04:08:56Z) - Enhancing Adversarial Training with Feature Separability [52.39305978984573]
We introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to boost the intra-class feature similarity and increase inter-class feature variance.
Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.
arXiv Detail & Related papers (2022-05-02T04:04:23Z) - Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness.
We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
arXiv Detail & Related papers (2020-10-26T04:44:43Z)
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.