75 citations · 85 across the 8 of their papers we have counts for
8 papers
BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
Jiatai Lin, Guoqiang Han, Xuemiao Xu +5
Class activation mapping~(CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation~(WSSS) and object…
Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification
Luyang Luo, Dunyuan Xu, Hao Chen +2
Deep learning models were frequently reported to learn from shortcuts like dataset biases. As deep learning is playing an increasingly important role in the modern healthcare syste…
Exploiting Aliasing for Manga Restoration
Minshan Xie, Menghan Xia, Tien-Tsin Wong
As a popular entertainment art form, manga enriches the line drawings details with bitonal screentones. However, manga resources over the Internet usually show screentone artifacts…
Enhance Convolutional Neural Networks with Noise Incentive Block
Menghan Xia, Yi Wang, Chu Han +1
As a generic modeling tool, Convolutional Neural Networks (CNNs) have been widely employed in image generation and translation tasks. However, when fed with a flat input, current C…
Binocular Tone Mapping with Improved Overall Contrast and Local Details
Zhuming Zhang, Xinghong Hu, Xueting Liu +1
Tone mapping is a commonly used technique that maps the set of colors in high-dynamic-range (HDR) images to another set of colors in low-dynamic-range (LDR) images, to fit the need…
360 Panorama Cloning on Sphere
Qiang Zhao, Liang Wan, Wei Feng +2
In this paper, we address a novel problem of cloning a patch of the source spherical panoramic image to the target spherical panoramic image, which we call 360 panorama cloning. Co…
Real-time Deep Video Deinterlacing
Haichao Zhu, Xueting Liu, Xiangyu Mao +1
Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth. But it presents annoying…
ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion
Guofeng Zhang, Haomin Liu, Zilong Dong +3
Structure-from-motion (SfM) largely relies on feature tracking. In image sequences, if disjointed tracks caused by objects moving in and out of the field of view, occasional occlus…