Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet

• URL: http://arxiv.org/abs/2212.04871v2
• Date: Tue, 22 Aug 2023 15:00:06 GMT
• Title: Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet
• Authors: Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein
• Abstract summary: In this paper, we develop a framework that allows us to systematically identify spurious features in large datasets like ImageNet. We validate our results by showing that presence of the harmful spurious feature of a class alone is sufficient to trigger the prediction of that class. We introduce SpuFix as a simple mitigation method to reduce the dependence of any ImageNet classifier on previously identified harmful spurious features.
• Score: 36.48282338829549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can fail in unexpected ways. In this paper, we develop a framework that allows us to systematically identify spurious features in large datasets like ImageNet. It is based on our neural PCA components and their visualization. Previous work on spurious features often operates in toy settings or requires costly pixel-wise annotations. In contrast, we work with ImageNet and validate our results by showing that presence of the harmful spurious feature of a class alone is sufficient to trigger the prediction of that class. We introduce the novel dataset "Spurious ImageNet" which allows to measure the reliance of any ImageNet classifier on harmful spurious features. Moreover, we introduce SpuFix as a simple mitigation method to reduce the dependence of any ImageNet classifier on previously identified harmful spurious features without requiring additional labels or retraining of the model. We provide code and data at https://github.com/YanNeu/spurious_imagenet .

Related papers

• ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object [78.58860252442045]
  We introduce generative model as a data source for hard images that benchmark deep models' robustness. We are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Our work suggests that diffusion models can be an effective source to test vision models.
  arXiv  Detail & Related papers  (2024-03-27T17:23:39Z)
• Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation [14.016699770436961]
  We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Experiment results show that our method can generate spurious images that are consistently spurious across different classifiers.
  arXiv  Detail & Related papers  (2024-02-13T03:55:09Z)
• ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing [45.14977000707886]
  Higher accuracy on ImageNet usually leads to better robustness against different corruptions. We create a toolkit for object editing with controls of backgrounds, sizes, positions, and directions. We evaluate the performance of current deep learning models, including both convolutional neural networks and vision transformers.
  arXiv  Detail & Related papers  (2023-03-30T02:02:32Z)
• Core Risk Minimization using Salient ImageNet [53.616101711801484]
  We introduce the Salient Imagenet dataset with more than 1 million soft masks localizing core and spurious features for all 1000 Imagenet classes. Using this dataset, we first evaluate the reliance of several Imagenet pretrained models (42 total) on spurious features. Next, we introduce a new learning paradigm called Core Risk Minimization (CoRM) whose objective ensures that the model predicts a class using its core features.
  arXiv  Detail & Related papers  (2022-03-28T01:53:34Z)
• Causal ImageNet: How to discover spurious features in Deep Learning? [44.053067014796596]
  A key reason for the lack of reliability of deep neural networks in the real world is their heavy reliance on it spurious input features that are causally unrelated to the true label. In this work, we introduce a it scalable framework to discover a subset of spurious and causal visual attributes used in inferences of a general model. We show that these neural feature annotations it generalize extremely well to many more images it without any human supervision.
  arXiv  Detail & Related papers  (2021-10-08T15:55:05Z)
• Automated Cleanup of the ImageNet Dataset by Model Consensus, Explainability and Confident Learning [0.0]
  ImageNet was the backbone of various convolutional neural networks (CNNs) trained on ILSVRC12Net. This paper describes automated applications based on model consensus, explainability and confident learning to correct labeling mistakes. The ImageNet-Clean improves the model performance by 2-2.4 % for SqueezeNet and EfficientNet-B0 models.
  arXiv  Detail & Related papers  (2021-03-30T13:16:35Z)
• Shape-Texture Debiased Neural Network Training [50.6178024087048]
  Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. We develop an algorithm for shape-texture debiased learning. Experiments show that our method successfully improves model performance on several image recognition benchmarks.
  arXiv  Detail & Related papers  (2020-10-12T19:16:12Z)
• Are we done with ImageNet? [86.01120671361844]
  We develop a more robust procedure for collecting human annotations of the ImageNet validation set. We reassess the accuracy of recently proposed ImageNet classifiers, and find their gains to be substantially smaller than those reported on the original labels. The original ImageNet labels to no longer be the best predictors of this independently-collected set, indicating that their usefulness in evaluating vision models may be nearing an end.
  arXiv  Detail & Related papers  (2020-06-12T13:17:25Z)
• From ImageNet to Image Classification: Contextualizing Progress on Benchmarks [99.19183528305598]
  We study how specific design choices in the ImageNet creation process impact the fidelity of the resulting dataset. Our analysis pinpoints how a noisy data collection pipeline can lead to a systematic misalignment between the resulting benchmark and the real-world task it serves as a proxy for.
  arXiv  Detail & Related papers  (2020-05-22T17:39:16Z)

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.