Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

• URL: http://arxiv.org/abs/2303.13087v1
• Date: Thu, 23 Mar 2023 07:58:48 GMT
• Title: Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
• Authors: Zhuo Huang, Miaoxi Zhu, Xiaobo Xia, Li Shen, Jun Yu, Chen Gong, Bo Han, Bo Du, Tongliang Liu
• Abstract summary: Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error. We propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. We show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
• Score: 89.92932924515324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.

Related papers

• Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution [7.638042073679073]
  This paper explores the universality of various methods for enhancing the robustness of deep learning Super-Resolution models. We show that median randomized smoothing (MRS) is more general in terms of robustness compared to adversarial learning techniques. As expected, we also illustrate that the proposed universal robust method enables the SR model to handle standard corruptions more effectively.
  arXiv  Detail & Related papers  (2024-05-23T18:00:01Z)
• Learning Correction Errors via Frequency-Self Attention for Blind Image Super-Resolution [1.734165485480267]
  We introduce a novel blind SR approach that focuses on Learning Correction Errors (LCE) Within an SR network, we jointly optimize SR performance by utilizing both the original LR image and the frequency learning of the CLR image. Our approach effectively addresses the challenges associated with degradation estimation and correction errors, paving the way for more accurate blind image SR.
  arXiv  Detail & Related papers  (2024-03-12T07:58:14Z)
• Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications [31.3535638804615]
  Machine learning algorithms minimize average risk are susceptible to distributional shifts. distributionally robust optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. DRO suffers from over-pessimism, leading to low-confidence predictions, poor parameter estimations as well as poor generalization. In this work, we conduct a theoretical analysis of a probable root cause of over-pessimism: excessive focus on noisy samples.
  arXiv  Detail & Related papers  (2023-11-08T23:33:39Z)
• DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework [133.26230331320963]
  Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. We propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it.
  arXiv  Detail & Related papers  (2023-11-06T12:15:57Z)
• Domain Generalization without Excess Empirical Risk [83.26052467843725]
  A common approach is designing a data-driven surrogate penalty to capture generalization and minimize the empirical risk jointly with the penalty. We argue that a significant failure mode of this recipe is an excess risk due to an erroneous penalty or hardness in joint optimization. We present an approach that eliminates this problem. Instead of jointly minimizing empirical risk with the penalty, we minimize the penalty under the constraint of optimality of the empirical risk.
  arXiv  Detail & Related papers  (2023-08-30T08:46:46Z)
• Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers [9.979945269265627]
  We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR) We demonstrate reductions in test error rate by up to 83.5% and loss by up to 91.3% compared with baseline methods, by adopting a novel random training method.
  arXiv  Detail & Related papers  (2022-10-15T05:09:28Z)
• Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers [3.179831861897336]
  We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR) We demonstrate reductions in test error rate by up to 83.5% and loss by up to 91.3% compared with baseline methods, by adopting a novel random training method.
  arXiv  Detail & Related papers  (2021-09-27T02:58:19Z)
• Generalized Real-World Super-Resolution through Adversarial Robustness [107.02188934602802]
  We present Robust Super-Resolution, a method that leverages the generalization capability of adversarial attacks to tackle real-world SR. Our novel framework poses a paradigm shift in the development of real-world SR methods. By using a single robust model, we outperform state-of-the-art specialized methods on real-world benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T22:43:20Z)
• Improving robustness against common corruptions with frequency biased models [112.65717928060195]
  unseen image corruptions can cause a surprisingly large drop in performance. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation. We propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness.
  arXiv  Detail & Related papers  (2021-03-30T10:44:50Z)
• Best-Buddy GANs for Highly Detailed Image Super-Resolution [71.13466303340192]
  We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input. Most methods along this line rely on a predefined single-LR-single-HR mapping, which is not flexible enough for the SISR task. We propose best-buddy GANs (Beby-GAN) for rich-detail SISR. Relaxing the immutable one-to-one constraint, we allow the estimated patches to dynamically seek the best supervision.
  arXiv  Detail & Related papers  (2021-03-29T02:58:27Z)

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.