Deep Feature Response Discriminative Calibration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Wenxiang, Qiu, Tian, Zhou, Linyun, Feng, Zunlei, Song, Mingli, Wang, Huiqiong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910707013910528
author Xu, Wenxiang
Qiu, Tian
Zhou, Linyun
Feng, Zunlei
Song, Mingli
Wang, Huiqiong
author_facet Xu, Wenxiang
Qiu, Tian
Zhou, Linyun
Feng, Zunlei
Song, Mingli
Wang, Huiqiong
contents Deep neural networks (DNNs) have numerous applications across various domains. Several optimization techniques, such as ResNet and SENet, have been proposed to improve model accuracy. These techniques improve the model performance by adjusting or calibrating feature responses according to a uniform standard. However, they lack the discriminative calibration for different features, thereby introducing limitations in the model output. Therefore, we propose a method that discriminatively calibrates feature responses. The preliminary experimental results indicate that the neural feature response follows a Gaussian distribution. Consequently, we compute confidence values by employing the Gaussian probability density function, and then integrate these values with the original response values. The objective of this integration is to improve the feature discriminability of the neural feature response. Based on the calibration values, we propose a plugin-based calibration module incorporated into a modified ResNet architecture, termed Response Calibration Networks (ResCNet). Extensive experiments on datasets like CIFAR-10, CIFAR-100, SVHN, and ImageNet demonstrate the effectiveness of the proposed approach. The developed code is publicly available at https://github.com/tcmyxc/ResCNet.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13582
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Feature Response Discriminative Calibration
Xu, Wenxiang
Qiu, Tian
Zhou, Linyun
Feng, Zunlei
Song, Mingli
Wang, Huiqiong
Computer Vision and Pattern Recognition
Deep neural networks (DNNs) have numerous applications across various domains. Several optimization techniques, such as ResNet and SENet, have been proposed to improve model accuracy. These techniques improve the model performance by adjusting or calibrating feature responses according to a uniform standard. However, they lack the discriminative calibration for different features, thereby introducing limitations in the model output. Therefore, we propose a method that discriminatively calibrates feature responses. The preliminary experimental results indicate that the neural feature response follows a Gaussian distribution. Consequently, we compute confidence values by employing the Gaussian probability density function, and then integrate these values with the original response values. The objective of this integration is to improve the feature discriminability of the neural feature response. Based on the calibration values, we propose a plugin-based calibration module incorporated into a modified ResNet architecture, termed Response Calibration Networks (ResCNet). Extensive experiments on datasets like CIFAR-10, CIFAR-100, SVHN, and ImageNet demonstrate the effectiveness of the proposed approach. The developed code is publicly available at https://github.com/tcmyxc/ResCNet.
title Deep Feature Response Discriminative Calibration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.13582