Ablation Path Saliency
Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. Unfortunately, the different methods may disagree and it can be hard to quantify how representative and faithful the explanation really is. We observe however that several of these methods can be seen as edge cases of a single, more general procedure based on finding a particular path through the classifier's domain. This offers additional geometric interpretation to the existing methods. We demonstrate furthermore that ablation paths can be directly used as a technique of its own right. This is able to compete with literature methods on existing benchmarks, while giving more fine-grained information and better opportunities for validation of the explanations' faithfulness.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training
Neural networks are widely used in various NLP tasks for their remarkable performance. However, the complexity makes them difficult to interpret, i.e., they are not guaranteed right for the right reason. Besides the comp…
Contrastive LearningMedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio
Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification. Conventional augmentation can improve training diversity but may distort diagnostically i…
Medical Image ClassificationImage AugmentationSalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images
This paper introduces a new framework to predict visual attention of omnidirectional images. The key setup of our architecture is the simultaneous prediction of the saliency map and a corresponding scanpath for a given s…
DecoderPredictionScanpath predictionSaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes
We introduce SaltiNet, a deep neural network for scanpath prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first …
Scanpath predictionSG-CLDFF: A Novel Framework for Automated White Blood Cell Classification and Segmentation
Accurate segmentation and classification of white blood cells (WBCs) in microscopic images are essential for diagnosis and monitoring of many hematological disorders, yet remain challenging due to staining variability, c…