activity
20202022
most citedVision Transformer with Convolutions Architecture Search

5 citations · 14 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV20222 cited

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

Haichao Zhang, Jiashi Li, Xin Xia +2

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the ima…

cs.CV20225 cited

Vision Transformer with Convolutions Architecture Search

Haichao Zhang, Kuangrong Hao, Witold Pedrycz +3

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of…

cs.CV2021

Enhanced Gradient for Differentiable Architecture Search

Haichao Zhang, Kuangrong Hao, Lei Gao +2

In recent years, neural architecture search (NAS) methods have been proposed for the automatic generation of task-oriented network architecture in image classification. However, th…

cs.CV20211 cited

MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images

Bing Wei, Kuangrong Hao, Lei Gao

For the sake of recognizing and classifying textile defects, deep learning-based methods have been proposed and achieved remarkable success in single-label textile images. However,…

cs.CV20201 cited

Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent

Haichao Zhang, Kuangrong Hao, Lei Gao +2

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivit…