Hong Liu

Dr. Hong Liu

National Institute of Informatics, Tokyo 101-8430, Japan

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 May 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZYZhengwei Yang
Zhengwei Yang
Xian ZhongXian Zhong
Xian Zhong
Zhun ZhongZhun Zhong
Zhun Zhong
Hong LiuHong Liu
Hong Liu
Zheng WangZheng Wang
Zheng Wang
SSShin'Ichi Satoh
Shin'Ichi Satoh
Recent person Re-IDentification (ReID) systems have been challenged by changes in personnel clothing, leading to the study of Cloth-Changing person ReID (CC-ReID). Commonly used techniques involve incorporating auxiliary information ( e.g ., body masks, gait, skeleton, and keypoints) to accurately identify the target pedestrian. However, the effectiveness of these methods heavily relies on the quality of auxiliary information and comes at the cost of additional computational resources, ultimately increasing system complexity. This paper focuses on achieving CC-ReID by effectively leveraging the information concealed within the image. To this end, we introduce an Auxiliary-free Competitive IDentification (ACID) model. It achieves a win-win situation by enriching the identity (ID)-preserving information conveyed by the appearance and structure features while maintaining holistic efficiency. In detail, we build a hierarchical competitive strategy that progressively accumulates meticulous ID cues with discriminating feature extraction at the global, channel, and pixel levels during model inference. After mining the hierarchical discriminative clues for appearance and structure features, these enhanced ID-relevant features are crosswise integrated to reconstruct images for reducing intra-class variations. Finally, by combing with self- and cross-ID penalties, the ACID is trained under a generative adversarial learning framework to effectively minimize the distribution discrepancy between the generated data and real-world data. Experimental results on four public cloth-changing datasets ( i.e ., PRCC-ReID, VC-Cloth, LTCC-ReID, and Celeb-ReID) demonstrate the proposed ACID can achieve superior performance over state-of-the-art methods. The code is available soon at: https://github.com/BoomShakaY/Win-CCReID.

8 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
KSKe Sun
Ke Sun
ZCZhongxi Chen
Zhongxi Chen
XLXianming Lin
Xianming Lin
XSXiaoshuai Sun
Xiaoshuai Sun
Hong LiuHong Liu
Hong Liu
RJRongrong Ji
Rongrong Ji
Camouflaged Object Detection (COD) poses a significant challenge in computer vision, playing a critical role in applications. Existing COD methods often exhibit challenges in accurately predicting nuanced boundaries with high-confidence predictions. In this work, we introduce CamoDiffusion, a new learning method that employs a conditional diffusion model to generate masks that progressively refine the boundaries of camouflaged objects. In particular, we first design an adaptive transformer conditional network, specifically designed for integration into a Denoising Network, which facilitates iterative refinement of the saliency masks. Second, based on the classical diffusion model training, we investigate a variance noise schedule and a structure corruption strategy, which aim to enhance the accuracy of our denoising model by effectively handling uncertain input. Third, we introduce a Consensus Time Ensemble technique, which integrates intermediate predictions using a sampling mechanism, thus reducing overconfidence and incorrect predictions. Finally, we conduct extensive experiments on three benchmark datasets that show that: 1) the efficacy and universality of our method is demonstrated in both camouflaged and salient object detection tasks. 2) compared to existing state-of-the-art methods, CamoDiffusion demonstrates superior performance 3) CamoDiffusion offers flexible enhancements, such as an accelerated version based on the VQ-VAE model and a skip approach.

30 July 2022 in Machine Intelligence Research
Verified
Journal Article
Open access
PDF file
DFDeng-Ping Fan
Deng-Ping Fan
ZHZiling Huang
Ziling Huang
PZPeng Zheng
Peng Zheng
Hong LiuHong Liu
Hong Liu
XQXuebin Qin
Xuebin Qin
LGLuc Van Gool
Luc Van Gool
This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of obtaining hand-drawn sketch datasets, there is a lack of a complete benchmark for assessing the development of FSS algorithms over the last decade. We first introduce a high-quality dataset for FSS, named FS2K, which consists of 2 104 image-sketch pairs spanning three types of sketch styles, image backgrounds, lighting conditions, skin colors, and facial attributes. FS2K differs from previous FSS datasets in difficulty, diversity, and scalability and should thus facilitate the progress of FSS research. Second, we present the largest-scale FSS investigation by reviewing 89 classic methods, including 25 handcrafted feature-based facial-sketch synthesis approaches, 29 general translation methods, and 35 image-to-sketch approaches. In addition, we elaborate comprehensive experiments on the existing 19 cutting-edge models. Third, we present a simple baseline for FSS, named FSGAN. With only two straightforward components, i.e., facial-aware masking and style-vector expansion, our FSGAN surpasses the performance of all previous state-of-the-art models on the proposed FS2K dataset by a large margin. Finally, we conclude with lessons learned over the past years and point out several unsolved challenges. Our code is available at https://github.com/DengPingFan/FSGAN.

6 May 2020 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
MLMingbao Lin
Mingbao Lin
RJRongrong Ji
Rongrong Ji
Hong LiuHong Liu
Hong Liu
XSXiaoshuai Sun
Xiaoshuai Sun
SCShen Chen
Shen Chen
QTQi Tian
Qi Tian

29 January 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HKHuafeng Kuang
Huafeng Kuang
Hong LiuHong Liu
Hong Liu
XLXianming Lin
Xianming Lin
RJRongrong Ji
Rongrong Ji
Recent works have indicated that deep neural networks (DNNs) are vulnerable to adversarial attacks, wherein an attacker perturbs an input example with human-imperceptible noise that can easily fool the DNNs, resulting in incorrect predictions. This severely limits the application of deep learning in security-critical scenarios, such as face authentication. Adversarial training (AT) is one of the most practical approaches to strengthening the robustness of DNNs. However, existing AT-based methods treat each training sample independently, thereby ignoring the underlying topological structure in the training data. To this end, in this paper, we take full advantage of the topology information and introduce a Topology Aligning Adversarial Training (TAAT) algorithm. TAAT aims to encourage the trained model to maintain consistency in the topological structure within the feature space of both natural and adversarial examples. To ensure the stability and efficiency of topology alignment, we further introduce a novel Knowledge-Guided (KG) training scheme. This scheme explicitly aligns local logit outputs with global topological structures, leveraging a robust auxiliary model to enhance the target model’s performance. To verify the effectiveness of the proposed method, we conduct extensive experiments on popular benchmark datasets ( e.g ., CIFAR and ImageNet) and evaluate the robustness against state-of-the-art adversarial attacks ( e.g ., PGD-attack and AutoAttack). The experimental results demonstrate that the proposed method has superior robustness over the previous state-of-the-art methods. Our code and pre-trained models are available at https://github.com/SkyKuang/TAAT.

3 November 2022
Verified
Book Chapter
Closed access
PDF file
YWYixu Wang
Yixu Wang
JLJie Li
Jie Li
Hong LiuHong Liu
Hong Liu
YWYan Wang
Yan Wang
YWYongjian Wu
Yongjian Wu
RJRongrong Ji
Rongrong Ji