7 papers
ProtoSolo: Interpretable Image Classification via Single-Prototype Activation
Yitao Peng, Lianghua He, Hongzhou Chen
Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making in…
Hierarchical Salient Patch Identification for Interpretable Fundus Disease Localization
Yitao Peng, Lianghua He, Die Hu
With the widespread application of deep learning technology in medical image analysis, the effective explanation of model predictions and improvement of diagnostic accuracy have be…
FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations
Yitao Peng, Lianghua He, Die Hu +3
Interpretable deep learning models have received widespread attention in the field of image recognition. Due to the unique multi-instance learning of medical images and the difficu…
Hierarchical Dynamic Masks for Visual Explanation of Neural Networks
Yitao Peng, Longzhen Yang, Yihang Liu +1
Saliency methods generating visual explanatory maps representing the importance of image pixels for model classification is a popular technique for explaining neural network decisi…
Decoupling Deep Learning for Interpretable Image Recognition
Yitao Peng, Yihang Liu, Longzhen Yang +1
The interpretability of neural networks has recently received extensive attention. Previous prototype-based explainable networks involved prototype activation in both reasoning and…
MDM: Multiple Dynamic Masks for Visual Explanation of Neural Networks
Yitao Peng, Longzhen Yang, Yihang Liu +1
The Class Activation Map (CAM) lookup of a neural network tells us to which regions the neural network focuses when it makes a decision. In the past, the CAM search method was depe…
Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning
Longzhen Yang, Yihang Liu, Yitao Peng +1
Accuracy and Diversity are two essential metrizable manifestations in generating natural and semantically correct captions. Many efforts have been made to enhance one of them with…