Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization

• URL: http://arxiv.org/abs/2012.02166v1
• Date: Thu, 3 Dec 2020 18:48:39 GMT
• Title: Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization
• Authors: Shir Gur, Ameen Ali, Lior Wolf
• Abstract summary: We develop an algorithm that provides per-class explainability. In an extensive battery of experiments, we demonstrate the ability of our methods to class-specific visualization.
• Score: 87.96102461221415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name {\em the saliency bias} hypothesis. In this work, we integrate two lines of research: gradient-based methods and attribution-based methods, and develop an algorithm that provides per-class explainability. The algorithm back-projects the per pixel local influence, in a manner that is guided by the local attributions, while correcting for salient features that would otherwise bias the explanation. In an extensive battery of experiments, we demonstrate the ability of our methods to class-specific visualization, and not just the predicted label. Remarkably, the method obtains state of the art results in benchmarks that are commonly applied to gradient-based methods as well as in those that are employed mostly for evaluating attribution methods. Using a new unsupervised procedure, our method is also successful in demonstrating that self-supervised methods learn semantic information.

Related papers

• The Impact of Semi-Supervised Learning on Line Segment Detection [11.636855122196323]
  We present a method for line segment detection in images, based on a semi-supervised framework. We show comparable results to fully supervised methods. Our method is to our knowledge the first to target line detection using modern state-of-the-art methodologies for semi-supervised learning.
  arXiv  Detail & Related papers  (2024-11-07T10:28:11Z)
• Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label [7.400926717561454]
  This paper investigates a framework for weakly-supervised object localization. It aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels.
  arXiv  Detail & Related papers  (2024-04-15T06:02:09Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Fine-Grained Visual Classification using Self Assessment Classifier [12.596520707449027]
  Extracting discriminative features plays a crucial role in the fine-grained visual classification task. In this paper, we introduce a Self Assessment, which simultaneously leverages the representation of the image and top-k prediction classes. We show that our method achieves new state-of-the-art results on CUB200-2011, Stanford Dog, and FGVC Aircraft datasets.
  arXiv  Detail & Related papers  (2022-05-21T07:41:27Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization [7.602783618330373]
  We propose a two-stage approach to learn more consistent localization. In the first stage, we propose a mask-based pseudo label generator algorithm, and use the pseudo-supervised learning method to initialize an object localization network. In the second stage, we propose a simple and effective method for evaluating the confidence of pseudo-labels based on classification discrimination.
  arXiv  Detail & Related papers  (2022-03-18T09:05:51Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Region Comparison Network for Interpretable Few-shot Image Classification [97.97902360117368]
  Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes. We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works. We also present a new way to generalize the interpretability from the level of tasks to categories.
  arXiv  Detail & Related papers  (2020-09-08T07:29:05Z)

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.