A Singular Value Perspective on Model Robustness

• URL: http://arxiv.org/abs/2012.03516v1
• Date: Mon, 7 Dec 2020 08:09:07 GMT
• Title: A Singular Value Perspective on Model Robustness
• Authors: Malhar Jere, Maghav Kumar, Farinaz Koushanfar
• Abstract summary: We show that naturally trained and adversarially robust CNNs exploit highly different features for the same dataset. We propose Rank Integrated Gradients (RIG), the first rank-based feature attribution method to understand the dependence of CNNs on image rank.
• Score: 14.591622269748974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional Neural Networks (CNNs) have made significant progress on several computer vision benchmarks, but are fraught with numerous non-human biases such as vulnerability to adversarial samples. Their lack of explainability makes identification and rectification of these biases difficult, and understanding their generalization behavior remains an open problem. In this work we explore the relationship between the generalization behavior of CNNs and the Singular Value Decomposition (SVD) of images. We show that naturally trained and adversarially robust CNNs exploit highly different features for the same dataset. We demonstrate that these features can be disentangled by SVD for ImageNet and CIFAR-10 trained networks. Finally, we propose Rank Integrated Gradients (RIG), the first rank-based feature attribution method to understand the dependence of CNNs on image rank.

Related papers

• The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach [11.524573224123905]
  CNNs make decisions based on narrow, specific regions of input images. This behavior can severely compromise the model's generalization capabilities. We introduce Saliency Guided Dropout (SGDrop) to address this specific issue.
  arXiv  Detail & Related papers  (2024-09-25T21:30:16Z)
• SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization [24.286426387100423]
  We propose a method that captures subtle changes by aggregating context-aware features from most relevant image-regions. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.
  arXiv  Detail & Related papers  (2022-09-05T19:43:15Z)
• Robustness and invariance properties of image classifiers [8.970032486260695]
  Deep neural networks have achieved impressive results in many image classification tasks. Deep networks are not robust to a large variety of semantic-preserving image modifications. The poor robustness of image classifiers to small data distribution shifts raises serious concerns regarding their trustworthiness.
  arXiv  Detail & Related papers  (2022-08-30T11:00:59Z)
• Image Quality Assessment using Contrastive Learning [50.265638572116984]
  We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
  arXiv  Detail & Related papers  (2021-10-25T21:01:00Z)
• BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks [65.2021953284622]
  We study robustness of CNNs against white-box and black-box adversarial attacks. Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
  arXiv  Detail & Related papers  (2021-03-14T20:43:19Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration [65.11022516031463]
  We present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction. In this paper, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies. Our presented DIN can be trained end-to-end and applied to various image restoration tasks.
  arXiv  Detail & Related papers  (2020-10-29T15:32:00Z)
• On Robustness and Transferability of Convolutional Neural Networks [147.71743081671508]
  Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. We study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time. We find that increasing both the training set and model sizes significantly improve the distributional shift robustness.
  arXiv  Detail & Related papers  (2020-07-16T18:39:04Z)
• The shape and simplicity biases of adversarially robust ImageNet-trained CNNs [9.707679445925516]
  We study the shape bias and internal mechanisms that enable the generalizability of AlexNet, GoogLeNet, and ResNet-50 models trained via adversarial training. Remarkably, adversarial training induces three simplicity biases into hidden neurons in the process of "robustifying" CNNs.
  arXiv  Detail & Related papers  (2020-06-16T16:38:16Z)
• Hold me tight! Influence of discriminative features on deep network boundaries [63.627760598441796]
  We propose a new perspective that relates dataset features to the distance of samples to the decision boundary. This enables us to carefully tweak the position of the training samples and measure the induced changes on the boundaries of CNNs trained on large-scale vision datasets.
  arXiv  Detail & Related papers  (2020-02-15T09:29:36Z)

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.