CASE: Contrastive Activation for Saliency Estimation

• URL: http://arxiv.org/abs/2506.07327v3
• Date: Sun, 15 Jun 2025 17:02:01 GMT
• Title: CASE: Contrastive Activation for Saliency Estimation
• Authors: Dane Williamson, Yangfeng Ji, Matthew Dwyer,
• Abstract summary: Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction.<n>We propose a diagnostic test for class sensitivity: a method's ability to distinguish between competing class labels on the same input.<n>We show that many widely used saliency methods produce nearly identical explanations regardless of the class label, calling into question their reliability.
• Score: 14.833454650943805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility can obscure critical limitations. In this work, we propose a diagnostic test for class sensitivity: a method's ability to distinguish between competing class labels on the same input. Through extensive experiments, we show that many widely used saliency methods produce nearly identical explanations regardless of the class label, calling into question their reliability. We find that class-insensitive behavior persists across architectures and datasets, suggesting the failure mode is structural rather than model-specific. Motivated by these findings, we introduce CASE, a contrastive explanation method that isolates features uniquely discriminative for the predicted class. We evaluate CASE using the proposed diagnostic and a perturbation-based fidelity test, and show that it produces faithful and more class-specific explanations than existing methods.

Related papers

• Multi-class Image Anomaly Detection for Practical Applications: Requirements and Robust Solutions [3.647905567437244]
  We propose Hierarchical Coreset (HierCore) to meet all defined requirements for anomaly detection.<n>HierCore operates effectively even without class labels, leveraging a hierarchical memory bank to estimate class-wise decision criteria.<n>Results show that HierCore consistently meets all requirements and maintains strong, stable performance across all settings.
  arXiv  Detail & Related papers  (2025-08-04T14:44:40Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes.<n>Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes.<n>We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• Demystifying amortized causal discovery with transformers [21.058343547918053]
  Supervised learning approaches for causal discovery from observational data often achieve competitive performance.<n>In this work, we investigate CSIvA, a transformer-based model promising to train on synthetic data and transfer to real data.<n>We bridge the gap with existing identifiability theory and show that constraints on the training data distribution implicitly define a prior on the test observations.
  arXiv  Detail & Related papers  (2024-05-27T08:17:49Z)
• CLIMAX: An exploration of Classifier-Based Contrastive Explanations [5.381004207943597]
  We propose a novel post-hoc model XAI technique that provides contrastive explanations justifying the classification of a black box. Our method, which we refer to as CLIMAX, is based on local classifiers. We show that we achieve better consistency as compared to baselines such as LIME, BayLIME, and SLIME.
  arXiv  Detail & Related papers  (2023-07-02T22:52:58Z)
• Sanity Checks for Saliency Methods Explaining Object Detectors [5.735035463793008]
  Saliency methods are frequently used to explain Deep Neural Network-based models. We perform sanity checks for object detection and define new qualitative criteria to evaluate the saliency explanations. We find that EfficientDet-D0 is the most interpretable method independent of the saliency method.
  arXiv  Detail & Related papers  (2023-06-04T17:57:51Z)
• Zero-shot Model Diagnosis [80.36063332820568]
  A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling.
  arXiv  Detail & Related papers  (2023-03-27T17:59:33Z)
• The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods [86.39044549664189]
  Anomaly detection algorithms for feature-vector data identify anomalies as outliers, but outlier detection has not worked well in deep learning. This paper proposes the Familiarity Hypothesis that these methods succeed because they are detecting the absence of familiar learned features rather than the presence of novelty. The paper concludes with a discussion of whether familiarity detection is an inevitable consequence of representation learning.
  arXiv  Detail & Related papers  (2022-03-04T18:32:58Z)
• Resolving label uncertainty with implicit posterior models [71.62113762278963]
  We propose a method for jointly inferring labels across a collection of data samples. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs.
  arXiv  Detail & Related papers  (2022-02-28T18:09:44Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)
• Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
  We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition. CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions. Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
  arXiv  Detail & Related papers  (2020-08-12T06:23:49Z)

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.