activity
20202026
most citedLightweight Pixel Difference Networks for Efficient Visual Representation Learning

54 citations · 70 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CV2026★ 1 cited

Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

Pan Yi, Weijie Li, Xiaodong Chen +3

Synthetic Aperture Radar (SAR) image recognition is vital for disaster monitoring, military reconnaissance, and ocean observation. However, large SAR image sizes hinder deep learni…

cs.CV2025

Rapid Salient Object Detection with Difference Convolutional Neural Networks

Zhuo Su, Li Liu, Matthias Müller +4

This paper addresses the challenge of deploying salient object detection (SOD) on resource-constrained devices with real-time performance. While recent advances in deep neural netw…

cs.CV2024★ 54 cited

Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

Zhuo Su, Jiehua Zhang, Longguang Wang +4

Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in…

cs.CV2023★ 1 cited

ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks

Peng Zhao, Jiehua Zhang, Bowen Peng +4

Network binarization exhibits great potential for deployment on resource-constrained devices due to its low computational cost. Despite the critical importance, the security of bin…

cs.CV2023

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

Zhuo Su, Jiehua Zhang, Tianpeng Liu +4

This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolut…

eess.IV2022

Boosting Binary Neural Networks via Dynamic Thresholds Learning

Jiehua Zhang, Xueyang Zhang, Zhuo Su +5

Developing lightweight Deep Convolutional Neural Networks (DCNNs) and Vision Transformers (ViTs) has become one of the focuses in vision research since the low computational cost i…