226 citations · 590 across the 36 of their papers we have counts for
10 papers · 1 filter
On the Dynamics Under the Unhinged Loss and Beyond
Xiong Zhou, Xianming Liu, Hanzhang Wang +3
Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the interm…
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Gang Wu, Junjun Jiang, Kui Jiang +1
Contrastive learning has emerged as a prevailing paradigm for high-level vision tasks, which, by introducing properly negative samples, has also been exploited for low-level vision…
Fully Convolutional Network for Lightweight Image Super-Resolution
Gang Wu, Junjun Jiang, Kui Jiang +1
Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ( or more). However, the heavy c…
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Lingdong Kong, Yaru Niu, Shaoyuan Xie +39
Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical a…
Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study
Yiqi Zhong, Xianming Liu, Deming Zhai +2
Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. Howev…
Super-Resolving Face Image by Facial Parsing Information
Chenyang Wang, Junjun Jiang, Zhiwei Zhong +2
Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one. In this paper, we build a novel parsing map guided fac…
Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution
Gang Wu, Junjun Jiang, Yuanchao Bai +1
In recent years, the use of large convolutional kernels has become popular in designing convolutional neural networks due to their ability to capture long-range dependencies and pr…
Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection
Zhenyu Li, Zhipeng Zhang, Heng Fan +4
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework. Specifically, having observed that the bottleneck of this…
Guided Depth Map Super-resolution: A Survey
Zhiwei Zhong, Xianming Liu, Junjun Jiang +2
Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution (HR) depth map from a low-resolution (LR) observation with the help of a paired HR color image…
Image Deblurring by Exploring In-depth Properties of Transformer
Pengwei Liang, Junjun Jiang, Xianming Liu +1
Image deblurring continues to achieve impressive performance with the development of generative models. Nonetheless, there still remains a displeasing problem if one wants to impro…