activity
20182022
most citedSelf-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube

15 citations · 73 across the 16 of their papers we have counts for

collaborators

18 papers

cs.CV20222 cited

Decoupled Mixup for Generalized Visual Recognition

Haozhe Liu, Wentian Zhang, Jinheng Xie +7

Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models oft…

cs.CV20221 cited

A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays

Haoqin Ji, Haozhe Liu, Yuexiang Li +7

Accurate abnormality localization in chest X-rays (CXR) can benefit the clinical diagnosis of various thoracic diseases. However, the lesion-level annotation can only be performed…

cs.CV20222 cited

Robust Representation via Dynamic Feature Aggregation

Haozhe Liu, Haoqin Ji, Yuexiang Li +5

Deep convolutional neural network (CNN) based models are vulnerable to the adversarial attacks. One of the possible reasons is that the embedding space of CNN based model is sparse…

cs.CV202214 cited

DFTR: Depth-supervised Fusion Transformer for Salient Object Detection

Heqin Zhu, Xu Sun, Yuexiang Li +3

Automated salient object detection (SOD) plays an increasingly crucial role in many computer vision applications. By reformulating the depth information as supervision rather than…

eess.IV20227 cited

Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retina OCT Images

Hong Liu, Dong Wei, Donghuan Lu +4

Automated surface segmentation of retinal layer is important and challenging in analyzing optical coherence tomography (OCT). Recently, many deep learning based methods have been d…

eess.IV20213 cited

InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction

Hong Wang, Yuexiang Li, Haimiao Zhang +4

For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT ima…