no code implementations • 23 Mar 2024 • Huiping Zhuang, Yuchen Liu, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Yi Wang, Lap-Pui Chau
Online Class Incremental Learning (OCIL) aims to train the model in a task-by-task manner, where data arrive in mini-batches at a time while previous data are not accessible.
1 code implementation • 23 Nov 2023 • YuFei Wang, Wenhan Yang, Xinyuan Chen, Yaohui Wang, Lanqing Guo, Lap-Pui Chau, Ziwei Liu, Yu Qiao, Alex C. Kot, Bihan Wen
Extensive experiments conducted on synthetic and real-world datasets demonstrate that the proposed method can achieve comparable or even superior performance compared to both previous SOTA methods and the teacher model, in just one sampling step, resulting in a remarkable up to x10 speedup for inference.
1 code implementation • NeurIPS 2023 • Tianyi Liu, Kejun Wu, Yi Wang, Wenyang Liu, Kim-Hui Yap, Lap-Pui Chau
The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment.
1 code implementation • ICCV 2023 • YuFei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex C. Kot, Bihan Wen
Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise.
Ranked #1 on Image Denoising on Image Denoising on SID x300
1 code implementation • 21 Jun 2023 • YuFei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex C. Kot, Bihan Wen
Besides, we propose a novel design of the context model, which can better predict the order masks of encoding/decoding based on both the sRGB image and the masks of already processed features.
no code implementations • 21 Jun 2023 • Shaohui Mei, Jiawei Lian, Xiaofei Wang, Yuru Su, Mingyang Ma, Lap-Pui Chau
Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS.
1 code implementation • 14 Apr 2023 • Wenyang Liu, Yi Wang, Kejun Wu, Kim-Hui Yap, Lap-Pui Chau
File fragment classification (FFC) on small chunks of memory is essential in memory forensics and Internet security.
1 code implementation • CVPR 2023 • Wenyang Liu, Yi Wang, Kim-Hui Yap, Lap-Pui Chau
In this paper, we study a real-world JPEG image restoration problem with bit errors on the encrypted bitstream.
1 code implementation • CVPR 2023 • YuFei Wang, Yi Yu, Wenhan Yang, Lanqing Guo, Lap-Pui Chau, Alex Kot, Bihan Wen
While raw images exhibit advantages over sRGB images (e. g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements.
no code implementations • 23 Feb 2023 • Andrea Piazzoni, Jim Cherian, Justin Dauwels, Lap-Pui Chau
In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves.
1 code implementation • 11 Feb 2023 • YuFei Wang, Renjie Wan, Wenhan Yang, Bihan Wen, Lap-Pui Chau, Alex C. Kot
Removing image artifacts from the scratched lens protector is inherently challenging due to the occasional flare artifacts and the co-occurring interference within mixed artifacts.
no code implementations • 21 Nov 2022 • Andrea Piazzoni, Jim Cherian, Roshan Vijay, Lap-Pui Chau, Justin Dauwels
In this paper, we introduce the notion of Cooperative Perception Error Models (coPEMs) towards achieving an effective and efficient integration of V2X solutions within a virtual test environment.
1 code implementation • 17 Feb 2022 • Haihan Tang, Yi Wang, Lap-Pui Chau
Specifically, TAFNet is divided into one main stream and two auxiliary streams.
1 code implementation • 13 Sep 2021 • YuFei Wang, Haoliang Li, Hao Cheng, Bihan Wen, Lap-Pui Chau, Alex C. Kot
Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain.
1 code implementation • 13 Sep 2021 • YuFei Wang, Renjie Wan, Wenhan Yang, Haoliang Li, Lap-Pui Chau, Alex C. Kot
To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many.
Ranked #3 on Low-Light Image Enhancement on Sony-Total-Dark
no code implementations • 17 Jul 2021 • Lisha Tang, Yi Wang, Lap-Pui Chau
Current part-level feature learning methods typically detect vehicle parts via uniform division, outside tools, or attention modeling.
no code implementations • 13 Jul 2021 • Jie Chen, Zaifeng Yang, Tsz Nam Chan, Hui Li, Junhui Hou, Lap-Pui Chau
A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.
no code implementations • 6 Jul 2021 • YuFei Wang, Haoliang Li, Lap-Pui Chau, Alex C. Kot
Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application.
2 code implementations • 3 Jun 2021 • Alexander Matyasko, Lap-Pui Chau
In this work, we introduce a fast, general and accurate adversarial attack that optimises the original non-convex constrained minimisation problem.
1 code implementation • 17 May 2021 • Nanyang Yang, Yi Wang, Lap-Pui Chau
The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network.
no code implementations • 4 May 2021 • Yunhao Zhou, Yi Wang, Lap-Pui Chau
Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serving as discriminative combination weights.
1 code implementation • 26 Apr 2021 • Yi Wang, Xinyu Hou, Lap-Pui Chau
In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet.
no code implementations • 30 Nov 2020 • Yi Wang, Zhen-Peng Bian, Yunhao Zhou, Lap-Pui Chau
Our study illustrates the outstanding design of ALPR with four insights: (1) the resampling-based cascaded framework is beneficial to both speed and accuracy; (2) the highly efficient license plate recognition should abundant additional character segmentation and recurrent neural network (RNN), but adopt a plain convolutional neural network (CNN); (3) in the case of CNN, taking advantage of vertex information on license plates improves the recognition performance; and (4) the weight-sharing character classifier addresses the lack of training images in small-scale datasets.
no code implementations • 15 Sep 2020 • Haoliang Li, Yufei Wang, Xiaofei Xie, Yang Liu, Shiqi Wang, Renjie Wan, Lap-Pui Chau, Alex C. Kot
In this paper, we propose a novel black-box backdoor attack technique on face recognition systems, which can be conducted without the knowledge of the targeted DNN model.
2 code implementations • 25 Jul 2020 • Yi Wang, Junhui Hou, Xinyu Hou, Lap-Pui Chau
In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i. e., objects are labeled with points) to estimate both the center points and sizes of crowded objects.
1 code implementation • ECCV 2020 • Mantang Guo, Junhui Hou, Jing Jin, Jie Chen, Lap-Pui Chau
Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms.
Image and Video Processing
no code implementations • 19 Apr 2020 • Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou, Yi Wang, Lap-Pui Chau
However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.
no code implementations • 26 Sep 2019 • Yi Wang, Zhen-Peng Bian, Junhui Hou, Lap-Pui Chau
That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures.
no code implementations • 7 Mar 2019 • Jie Chen, Lap-Pui Chau, Junhui Hou
A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities.
1 code implementation • NeurIPS 2018 • Alexander Matyasko, Lap-Pui Chau
Our main idea is: adversarial examples for the robust classifier should be indistinguishable from the regular data of the adversarial target.
no code implementations • 19 Aug 2018 • Jie Chen, Cheen-Hau Tan, Lap-Pui Chau
Vision based haze density estimation is of practical implications for the purpose of precaution alarm and emergency reactions toward disastrous hazy weathers.
no code implementations • 31 May 2018 • Jie Chen, Junhui Hou, Lap-Pui Chau
Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays.
no code implementations • 28 Apr 2018 • Muhammet Bastan, Kim-Hui Yap, Lap-Pui Chau
First, we detect the cars in each IR image using a convolutional neural network, which is pre-trained on regular RGB images and fine-tuned on IR images for higher accuracy.
no code implementations • 24 Apr 2018 • Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li
Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes.
no code implementations • CVPR 2018 • Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li
Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.
no code implementations • 13 Mar 2018 • Abrar H. Abdulnabi, Bing Shuai, Zhen Zuo, Lap-Pui Chau, Gang Wang
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation.
no code implementations • 7 Aug 2017 • Jie Chen, Junhui Hou, Yun Ni, Lap-Pui Chau
Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions.
no code implementations • 12 Oct 2016 • Jie Chen, Junhui Hou, Lap-Pui Chau
Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world.