no code implementations • 12 Apr 2024 • Chenqi Kong, Anwei Luo, Song Xia, Yi Yu, Haoliang Li, Alex C. Kot
Moreover, MoE-FFD leverages the expressivity of transformers and local priors of CNNs to simultaneously extract global and local forgery clues.
no code implementations • 28 Feb 2024 • Benjamin Walker, Andrew D. McLeod, Tiexin Qin, Yichuan Cheng, Haoliang Li, Terry Lyons
The core component of Log-NCDEs is the Log-ODE method, a tool from the study of rough paths for approximating a CDE's solution.
1 code implementation • 12 Feb 2024 • Hui Liu, Wenya Wang, Haoru Li, Haoliang Li
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia.
no code implementations • 9 Feb 2024 • Kecheng Chen, Elena Gal, Hong Yan, Haoliang Li
In this work, we propose to tackle the problem of domain generalization in the context of \textit{insufficient samples}.
no code implementations • 1 Dec 2023 • Tianlang He, Zhiqiu Xia, Jierun Chen, Haoliang Li, S. -H. Gary Chan
Unsupervised domain adaptation (UDA) seeks to bridge the domain gap between the target and source using unlabeled target data.
1 code implementation • 24 Nov 2023 • Hui Liu, Wenya Wang, Hao Sun, Anderson Rocha, Haoliang Li
We also propose a framework that simultaneously considers application scenarios of domain generalization (in which the target domain data is unavailable) and domain adaptation (in which unlabeled target domain data is available).
no code implementations • 30 Sep 2023 • Chenqi Kong, Anwei Luo, Shiqi Wang, Haoliang Li, Anderson Rocha, Alex C. Kot
Digital image forensics plays a crucial role in image authentication and manipulation localization.
1 code implementation • 20 Sep 2023 • Qian Ma, Zijian Zhang, Xiangyu Zhao, Haoliang Li, Hongwei Zhao, Yiqi Wang, Zitao Liu, Wanyu Wang
Then, we generate representative and common spatio-temporal patterns as global nodes to reflect a global dependency between sensors and provide auxiliary information for spatio-temporal dependency learning.
2 code implementations • 7 Sep 2023 • Rizhao Cai, Zitong Yu, Chenqi Kong, Haoliang Li, Changsheng chen, Yongjian Hu, Alex Kot
Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition system by presenting spoofed faces.
no code implementations • 12 Jun 2023 • Yu Chen, Yang Yu, Rongrong Ni, Yao Zhao, Haoliang Li
Next, we design a phoneme-viseme awareness module for cross-modal feature fusion and representation alignment, so that the modality gap can be reduced and the intrinsic complementarity of the two modalities can be better explored.
no code implementations • 9 Jun 2023 • João Phillipe Cardenuto, Jing Yang, Rafael Padilha, Renjie Wan, Daniel Moreira, Haoliang Li, Shiqi Wang, Fernanda Andaló, Sébastien Marcel, Anderson Rocha
Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive.
1 code implementation • 5 Jun 2023 • Yibing Liu, Chris Xing Tian, Haoliang Li, Lei Ma, Shiqi Wang
The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i. e., in-distribution (InD).
Ranked #2 on Out-of-Distribution Detection on ImageNet-1k vs Textures (AUROC metric)
2 code implementations • 10 May 2023 • Hui Liu, Wenya Wang, Haoliang Li
Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information.
no code implementations • ICCV 2023 • Rizhao Cai, Yawen Cui, Zhi Li, Zitong Yu, Haoliang Li, Yongjian Hu, Alex Kot
To alleviate the forgetting of previous domains without using previous data, we propose the Proxy Prototype Contrastive Regularization (PPCR) to constrain the continual learning with previous domain knowledge from the proxy prototypes.
no code implementations • 2 Mar 2023 • Chenqi Kong, Haoliang Li, Shiqi Wang
Nowadays, forgery faces pose pressing security concerns over fake news, fraud, impersonation, etc.
no code implementations • 28 Feb 2023 • Chenyu Yi, Siyuan Yang, YuFei Wang, Haoliang Li, Yap-Peng Tan, Alex C. Kot
To exploit information in video with self-supervised learning, TeCo uses global content from video clips and optimizes models for entropy minimization.
no code implementations • 26 Feb 2023 • Kecheng Chen, Haoliang Li, Renjie Wan, Hong Yan
Under this probabilistic framework, we propose to alleviate the noise distribution shifts between source and target domains via implicit noise modeling schemes in the latent space and image space, respectively.
no code implementations • 22 Feb 2023 • Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li
Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the superiority of our proposed approach compared to the baselines.
1 code implementation • 30 Jan 2023 • Chenqi Kong, Kexin Zheng, Yibing Liu, Shiqi Wang, Anderson Rocha, Haoliang Li
Face presentation attacks (FPA), also known as face spoofing, have brought increasing concerns to the public through various malicious applications, such as financial fraud and privacy leakage.
1 code implementation • 30 Nov 2022 • Jiaxing Li, Chenqi Kong, Shiqi Wang, Haoliang Li
The image recapture attack is an effective image manipulation method to erase certain forensic traces, and when targeting on personal document images, it poses a great threat to the security of e-commerce and other web applications.
no code implementations • 13 Nov 2022 • Yibing Liu, Chris Xing Tian, Haoliang Li, Shiqi Wang
Specifically, by treating feature elements as neuron activation states, we show that conventional alignment methods tend to deteriorate the diversity of learned invariant features, as they indiscriminately minimize all neuron activation differences.
no code implementations • 25 Oct 2022 • Rizhao Cai, Haoliang Li, Alex Kot
Filter pruning has been widely used for compressing convolutional neural networks to reduce computation costs during the deployment stage.
1 code implementation • 7 Oct 2022 • Hui Liu, Wenya Wang, Haoliang Li
In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attention mechanism and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm.
no code implementations • 29 Sep 2022 • Chenqi Kong, Shiqi Wang, Haoliang Li
With the rapid progress over the past five years, face authentication has become the most pervasive biometric recognition method.
1 code implementation • 25 Jul 2022 • Wang Lu, Jindong Wang, Haoliang Li, Yiqiang Chen, Xing Xie
Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i. e., the property within a domain, which is agnostic to other domains.
1 code implementation • 16 May 2022 • Tiexin Qin, Shiqi Wang, Haoliang Li
Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data.
1 code implementation • 8 May 2022 • Zhi Li, Rizhao Cai, Haoliang Li, Kwok-Yan Lam, Yongjian Hu, Alex C. Kot
Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD.
1 code implementation • 28 Jan 2022 • Yibing Liu, Haoliang Li, Yangyang Guo, Chenqi Kong, Jing Li, Shiqi Wang
Attention mechanisms are dominating the explainability of deep models.
no code implementations • 18 Oct 2021 • Zhi Li, Haoliang Li, Xin Luo, Yongjian Hu, Kwok-Yan Lam, Alex C. Kot
In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios.
1 code implementation • 13 Oct 2021 • Rizhao Cai, Zhi Li, Renjie Wan, Haoliang Li, Yongjian Hu, Alex ChiChung Kot
To improve the generalization ability, recent hybrid methods have been explored to extract task-aware handcrafted features (e. g., Local Binary Pattern) as discriminative information for the input of DNNs.
1 code implementation • 13 Oct 2021 • Chenyu Yi, Siyuan Yang, Haoliang Li, Yap-Peng Tan, Alex Kot
The state-of-the-art deep neural networks are vulnerable to common corruptions (e. g., input data degradations, distortions, and disturbances caused by weather changes, system error, and processing).
1 code implementation • 26 Sep 2021 • Hao Cheng, YuFei Wang, Haoliang Li, Alex C. Kot, Bihan Wen
In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications.
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
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 Jul 2021 • Chenqi Kong, Baoliang Chen, Haoliang Li, Shiqi Wang, Anderson Rocha, Sam Kwong
The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society.
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.
no code implementations • 1 Jul 2021 • Zhiming Li, Xiaofei Xie, Haoliang Li, Zhengzi Xu, Yi Li, Yang Liu
Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data.
no code implementations • 14 May 2021 • Chris Xing Tian, Haoliang Li, YuFei Wang, Shiqi Wang
However, due to the issue of limited dataset availability and the strict legal and ethical requirements for patient privacy protection, the broad applications of medical imaging classification driven by DNN with large-scale training data have been largely hindered.
no code implementations • 27 Feb 2021 • Chris Xing Tian, Haoliang Li, Xiaofei Xie, Yang Liu, Shiqi Wang
More specifically, by treating the DNN as a program and each neuron as a functional point of the code, during the network training we aim to improve the generalization capability by maximizing the neuron coverage of DNN with the gradient similarity regularization between the original and augmented samples.
no code implementations • 25 Jan 2021 • Baoliang Chen, Wenhan Yang, Haoliang Li, Shiqi Wang, Sam Kwong
The first branch aims to learn the camera invariant spoofing features via feature level decomposition in the high frequency domain.
1 code implementation • NeurIPS 2020 • Haoliang Li, YuFei Wang, Renjie Wan, Shiqi Wang, Tie-Qiang Li, Alex C. Kot
Recently, we have witnessed great progress in the field of medical imaging classification by adopting deep neural networks.
no code implementations • 16 Sep 2020 • Rizhao Cai, Haoliang Li, Shiqi Wang, Changsheng chen, Alex ChiChung Kot
Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i. e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative information, for the face anti-spoofing problem, we propose a novel framework based on the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN).
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.
no code implementations • 11 Sep 2020 • Yufei Wang, Haoliang Li, Alex C. Kot
One of the main drawbacks of deep Convolutional Neural Networks (DCNN) is that they lack generalization capability.
no code implementations • 19 Aug 2020 • Baoliang Chen, Haoliang Li, Hongfei Fan, Shiqi Wang
Here, we develop the first unsupervised domain adaptation based no reference quality assessment method for SCIs, leveraging rich subjective ratings of the natural images (NIs).
no code implementations • 3 Mar 2019 • Renjie Wan, Boxin Shi, Haoliang Li, Ling-Yu Duan, Alex C. Kot
Face images captured through the glass are usually contaminated by reflections.
no code implementations • 4 Jul 2018 • Shan Lin, Haoliang Li, Chang-Tsun Li, Alex ChiChung Kot
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training.
no code implementations • CVPR 2018 • Haoliang Li, Sinno Jialin Pan, Shiqi Wang, Alex C. Kot
In this paper, we tackle the problem of domain generalization: how to learn a generalized feature representation for an âunseenâ target domain by taking the advantage of multiple seen source-domain data.
Ranked #49 on Domain Generalization on PACS