Reproducibility review of "Why Not Other Classes": Towards Class-Contrastive Back-Propagation Explanations

2025-01-19 · Arvid Eriksson, Anton Israelsson, Mattias Kallhauge

"Why Not Other Classes?": Towards Class-Contrastive Back-Propagation Explanations (Wang & Wang, 2022) provides a method for contrastively explaining why a certain class in a neural network image classifier is chosen above others. This method consists of using back-propagation-based explanation methods from after the softmax layer rather than before. Our work consists of reproducing the work in the original paper. We also provide extensions to the paper by evaluating the method on XGradCAM, FullGrad, and Vision Transformers to evaluate its generalization capabilities. The reproductions show similar results as the original paper, with the only difference being the visualization of heatmaps which could not be reproduced to look similar. The generalization seems to be generally good, with implementations working for Vision Transformers and alternative back-propagation methods. We also show that the original paper suffers from issues such as a lack of detail in the method and an erroneous equation which makes reproducibility difficult. To remedy this we provide an open-source repository containing all code used for this project.

📄 PDF Abstract BibTeX arXiv:2501.11096

Code (1)

arvideriksson/contrastive-explanations 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision Boundary

2023-04-20 · Xiaokang Liu, Jianquan Li, Jingjing Mu, Min Yang 외

Open intent classification, which aims to correctly classify the known intents into their corresponding classes while identifying the new unknown (open) intents, is an essential but challenging task in dialogue systems. …

Contrastive Learning intent-classification Intent Classification

Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning

2025-01-16 · Parinita Nema, Vinod K Kurmi

Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the param…

class-incremental learning Class Incremental Learning Contrastive Learning Few-Shot Class-Incremental Learning+2

Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation

2023-03-24 · Weide Liu, Zhonghua Wu, Yang Zhao, Yuming Fang 외

Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized f…

Few-Shot Semantic Segmentation Generalized Few-Shot Semantic Segmentation Segmentation Semantic Segmentation

Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation

2024-07-06 · Haolin Pan, Yong Guo, Mianjie Yu, Jian Chen

Real-world data often follows a long-tailed distribution, where a few head classes occupy most of the data and a large number of tail classes only contain very limited samples. In practice, deep models often show poor ge…

Contrastive Learning Data Augmentation Image Classification Long-tail Learning

Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

2020-10-30 · Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong 외

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross…

Contrastive Learning General Classification Representation Learning Sentiment Analysis+1