# Multi-view Feature Augmentation with Adaptive Class Activation Mapping

Source: [Multi-view Feature Augmentation with Adaptive Class Activation Mapping](<https://www.sota2.com/research/paper/68fa72371e209131cea55012>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:30:07.638Z

Authors: Xiang Gao, Yingjie Tian, Zhiquan Qi

Published: 2022-06-26T19:05:27.000Z

## Abstract

We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1$\\times$1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2206.12943>)

[PDF](<https://arxiv.org/pdf/2206.12943.pdf>)