86 citations · 294 across the 26 of their papers we have counts for
15 papers · 1 filter
An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training
Yiju Yang, Tianxiao Zhang, Guanyu Li +2
In this paper, we propose a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more doma…
Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence
Wenchi Ma, Tianxiao Zhang, Guanghui Wang
Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by t…
Semantic Clustering based Deduction Learning for Image Recognition and Classification
Wenchi Ma, Xuemin Tu, Bo Luo +1
The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains. Human beings can make judgments based on experienc…
Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network
Usman Sajid, Guanghui Wang
The paper focuses on improving the recent plug-and-play patch rescaling module (PRM) based approaches for crowd counting. In order to make full use of the PRM potential and obtain…
A Discriminative Channel Diversification Network for Image Classification
Krushi Patel, Guanghui Wang
Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks. However, the performance improvement comes with add…
Audio-Visual Transformer Based Crowd Counting
Usman Sajid, Xiangyu Chen, Hasan Sajid +2
Crowd estimation is a very challenging problem. The most recent study tries to exploit auditory information to aid the visual models, however, the performance is limited due to the…
Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
Yiju Yang, Taejoon Kim, Guanghui Wang
Adversarial training based on the maximum classifier discrepancy between two classifier structures has achieved great success in unsupervised domain adaptation tasks for image clas…
Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation
Krushi Patel, Andres M. Bur, Guanghui Wang
Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer. However, polyp segmentation is a challenging task due to the di…
A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild
Kamala Gajurel, Cuncong Zhong, Guanghui Wang
Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition o…
Few-Shot Learning by Integrating Spatial and Frequency Representation
Xiangyu Chen, Guanghui Wang
Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algori…
SGNet: A Super-class Guided Network for Image Classification and Object Detection
Kaidong Li, Nina Y. Wang, Yiju Yang +1
Most classification models treat different object classes in parallel and the misclassifications between any two classes are treated equally. In contrast, human beings can exploit…
Parallel Scale-wise Attention Network for Effective Scene Text Recognition
Usman Sajid, Michael Chow, Jin Zhang +2
The paper proposes a new text recognition network for scene-text images. Many state-of-the-art methods employ the attention mechanism either in the text encoder or decoder for the…
Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations
Kaidong Li, Mohammad I. Fathan, Krushi Patel +6
Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effectiv…
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
Lei He, Jiwen Lu, Guanghui Wang +2
Depth estimation and semantic segmentation play essential roles in scene understanding. The state-of-the-art methods employ multi-task learning to simultaneously learn models for t…
Six-channel Image Representation for Cross-domain Object Detection
Tianxiao Zhang, Wenchi Ma, Guanghui Wang
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the d…