Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation

• URL: http://arxiv.org/abs/2402.18919v3
• Date: Sun, 21 Jul 2024 12:22:05 GMT
• Title: Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• Authors: Fahimeh Hosseini Noohdani, Parsa Hosseini, Aryan Yazdan Parast, Hamidreza Yaghoubi Araghi, Mahdieh Soleymani Baghshah,
• Abstract summary: We propose Decompose-and-Compose (DaC) to improve correlation shift by combining elements of images. Based on our observations, models trained with Empirical Risk Minimization (ERM) usually highly attend to either the causal components or the components having a high spurious correlation with the label. We propose a group-balancing method by intervening on images without requiring group labels or information regarding the spurious features during training.
• Score: 2.273629240935727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samples. One of the main sources of distribution shift for image classification is the compositional nature of images. Specifically, in addition to the main object or component(s) determining the label, some other image components usually exist, which may lead to the shift of input distribution between train and test environments. More importantly, these components may have spurious correlations with the label. To address this issue, we propose Decompose-and-Compose (DaC), which improves robustness to correlation shift by a compositional approach based on combining elements of images. Based on our observations, models trained with ERM usually highly attend to either the causal components or the components having a high spurious correlation with the label (especially in datapoints on which models have a high confidence). In fact, according to the amount of spurious correlation and the easiness of classification based on the causal or non-causal components, the model usually attends to one of these more (on samples with high confidence). Following this, we first try to identify the causal components of images using class activation maps of models trained with ERM. Afterward, we intervene on images by combining them and retraining the model on the augmented data, including the counterfactual ones. Along with its high interpretability, this work proposes a group-balancing method by intervening on images without requiring group labels or information regarding the spurious features during training. The method has an overall better worst group accuracy compared to previous methods with the same amount of supervision on the group labels in correlation shift.

Related papers

• Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise [25.764939424940284]
  We show how to fill in underrepresented samples of a particular label class using pseudo-images. While existing algorithms exclusively train on pseudo-images, our augmented client datasets consist of both real and pseudo-images. We demonstrate that small amounts of augmentation via mixups and natural noise markedly improve label-skewed CIFAR-10 and MNIST training.
  arXiv  Detail & Related papers  (2024-09-20T05:44:43Z)
• Common-Sense Bias Discovery and Mitigation for Classification Tasks [16.8259488742528]
  We propose a framework to extract feature clusters in a dataset based on image descriptions. The analyzed features and correlations are human-interpretable, so we name the method Common-Sense Bias Discovery (CSBD) Experiments show that our method discovers novel biases on multiple classification tasks for two benchmark image datasets.
  arXiv  Detail & Related papers  (2024-01-24T03:56:07Z)
• Debiasing Counterfactuals In the Presence of Spurious Correlations [0.98342301244574]
  We introduce the first end-to-end training framework that integrates both (i) popular debiasing classifiers and (ii) counterfactual image generation. We demonstrate that the debiasing method: learns generalizable markers across the population, and (ii) successfully ignores spurious correlations and focuses on the underlying disease pathology.
  arXiv  Detail & Related papers  (2023-08-21T19:01:45Z)
• Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases [8.455991178281469]
  We present benchmark-O2O, M2M-Easy, Medium, Hard, an image classification benchmark suite containing spurious correlations between classes and backgrounds. The resulting dataset is of high quality and contains approximately 152k images.
  arXiv  Detail & Related papers  (2023-03-09T18:22:12Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Learning to Annotate Part Segmentation with Gradient Matching [58.100715754135685]
  This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN. In particular, we formulate the annotator learning as a learning-to-learn problem. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images.
  arXiv  Detail & Related papers  (2022-11-06T01:29:22Z)
• Causal Transportability for Visual Recognition [70.13627281087325]
  We show that standard classifiers fail because the association between images and labels is not transportable across settings. We then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification.
  arXiv  Detail & Related papers  (2022-04-26T15:02:11Z)
• Understanding out-of-distribution accuracies through quantifying difficulty of test samples [10.266928164137635]
  Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the out-of-distribution (OOD) datasets. We propose a new metric to quantify the difficulty of the test images (either ID or OOD) that depends on the interaction of the training dataset and the model.
  arXiv  Detail & Related papers  (2022-03-28T21:13:41Z)
• Learning from Partially Overlapping Labels: Image Segmentation under Annotation Shift [68.6874404805223]
  We propose several strategies for learning from partially overlapping labels in the context of abdominal organ segmentation. We find that combining a semi-supervised approach with an adaptive cross entropy loss can successfully exploit heterogeneously annotated data.
  arXiv  Detail & Related papers  (2021-07-13T09:22:24Z)
• Background Splitting: Finding Rare Classes in a Sea of Background [55.03789745276442]
  We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories. In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset is background) We demonstrate that both standard fine-tuning approaches and state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in the presence of this extreme imbalance.
  arXiv  Detail & Related papers  (2020-08-28T23:05:15Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)

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.