paper-with-me

Papers

Exploring Gradient Flow Based Saliency for DNN Model Compression

2021-10-24 · Xinyu Liu, Baopu Li, Zhen Chen, Yixuan Yuan

Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead. Traditional model pruning methods such as l-1 pruning that evaluates the channel significance for DNN pay too much attention to the local analysis of each channel and make use of the magnitude of the entire feature while ignoring its relevance to the batch normalization (BN) and ReLU layer after each convolutional operation. To overcome these problems, we propose a new model pruning method from a new perspective of gradient flow in this paper. Specifically, we first theoretically analyze the channel's influence based on Taylor expansion by integrating the effects of BN layer and ReLU activation function. Then, the incorporation of the first-order Talyor polynomial of the scaling parameter and the shifting parameter in the BN layer is suggested to effectively indicate the significance of a channel in a DNN. Comprehensive experiments on both image classification and image denoising tasks demonstrate the superiority of the proposed novel theory and scheme. Code is available at https://github.com/CityU-AIM-Group/GFBS.

📄 PDF Abstract BibTeX arXiv:2110.12477

Code (1)

cityu-aim-group/gfbs 공식 구현 pytorch

Tasks

Denoisingimage-classificationImage ClassificationImage DenoisingModel Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

How do people explore virtual environments?

2016-12-13 · Vincent Sitzmann, Ana Serrano, Amy Pavel, Maneesh Agrawala 외

Understanding how people explore immersive virtual environments is crucial for many applications, such as designing virtual reality (VR) content, developing new compression algorithms, or learning computational models of…

Video Synopsis

Reasoning Fails Where Step Flow Breaks

2026-04-08 · Xiaoyu Xu, Yulan Pan, Xiaosong Yuan, Zhihong Shen 외 arxiv

Large reasoning models (LRMs) that generate long chains of thought now perform well on multi-step math, science, and coding tasks. However, their behavior is still unstable and hard to interpret, and existing analysis to…

Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach

2020-09-29 · Nicholas Halliwell, Freddy Lecue

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a predict…

General Classificationimage-classificationImage Classification

SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation

2026-04-28 · Ali Karkehabadi, Jamshid Hassanpour, Houman Homayoun, Avesta Sasan arxiv

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fun…

TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

2021-10-11 · Lin Cheng, Pengfei Fang, Yanjie Liang, Liao Zhang 외

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convoluti…