no code implementations • 17 Apr 2024 • Chaoxi Niu, Guansong Pang, Ling Chen
Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks.
1 code implementation • 16 Apr 2024 • Jiangning Zhang, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Zhucun Xue, Yong liu, Guansong Pang, DaCheng Tao
Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods.
1 code implementation • 4 Apr 2024 • Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng
Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 15 Mar 2024 • Yukun Li, Guansong Pang, Wei Suo, Chenchen Jing, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang
Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset.
2 code implementations • 11 Mar 2024 • Jiawen Zhu, Guansong Pang
In this work, we propose to train a GAD model with few-shot normal images as sample prompts for AD on diverse datasets on the fly.
1 code implementation • 19 Feb 2024 • Hezhe Qiao, Qingsong Wen, XiaoLi Li, Ee-Peng Lim, Guansong Pang
This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the unsupervised setting in most GAD studies with a fully unlabeled graph.
no code implementations • 29 Jan 2024 • Yunkang Cao, Xiaohao Xu, Jiangning Zhang, Yuqi Cheng, Xiaonan Huang, Guansong Pang, Weiming Shen
Visual Anomaly Detection (VAD) endeavors to pinpoint deviations from the concept of normality in visual data, widely applied across diverse domains, e. g., industrial defect inspection, and medical lesion detection.
1 code implementation • 17 Dec 2023 • Wenjun Miao, Guansong Pang, Tianqi Li, Xiao Bai, Jin Zheng
To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence.
1 code implementation • 16 Dec 2023 • Ruohuan Fang, Guansong Pang, Xiao Bai
This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information.
1 code implementation • 19 Nov 2023 • Yuting Sun, Guansong Pang, Guanhua Ye, Tong Chen, Xia Hu, Hongzhi Yin
The ongoing challenges in time series anomaly detection (TSAD), notably the scarcity of anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a more efficient solution.
no code implementations • 13 Nov 2023 • Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang
Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task.
no code implementations • 12 Nov 2023 • Qizhou Wang, Guansong Pang, Mahsa Salehi, Christopher Leckie
However, current methods tend to over-emphasise fitting the seen anomalies, leading to a weak generalisation ability to detect unseen anomalies, i. e., those that are not illustrated by the labelled anomaly nodes.
3 code implementations • 29 Oct 2023 • Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, Jiming Chen
It is a crucial task when training data is not accessible due to various concerns, eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly.
1 code implementation • 19 Oct 2023 • Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang
Extensive experiments on nine real-world anomaly detection datasets show that AHL can 1) substantially enhance different state-of-the-art OSAD models in detecting seen and unseen anomalies, and 2) effectively generalize to unseen anomalies in new domains.
no code implementations • 9 Oct 2023 • Feiyi Chen, Zhen Qin, Yingying Zhang, Shuiguang Deng, Yi Xiao, Guansong Pang, Qingsong Wen
Retraining a large neural network model with limited data is vulnerable to overfitting.
1 code implementation • 31 Aug 2023 • Ruohuan Fang, Guansong Pang, Lei Zhou, Xiao Bai, Jin Zheng
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge.
1 code implementation • 28 Aug 2023 • Jiaxi Li, Guansong Pang, Ling Chen, Mohammad-Reza Namazi-Rad
To address the problem, we propose HRGCN, an unsupervised deep heterogeneous graph neural network, to model complex heterogeneous relations between different entities in the system for effectively identifying these anomalous behaviour graphs.
1 code implementation • 22 Aug 2023 • Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang
With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task.
1 code implementation • 25 Jul 2023 • Hongzuo Xu, Yijie Wang, Guansong Pang, Songlei Jian, Ning Liu, Yongjun Wang
anomaly contamination.
Semi-supervised Anomaly Detection Supervised Anomaly Detection +1
1 code implementation • 7 Jul 2023 • Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning
Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes.
1 code implementation • 3 Jul 2023 • Chaoxi Niu, Guansong Pang, Ling Chen
One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole.
1 code implementation • 16 Jun 2023 • Kexin Zhang, Qingsong Wen, Chaoli Zhang, Rongyao Cai, Ming Jin, Yong liu, James Zhang, Yuxuan Liang, Guansong Pang, Dongjin Song, Shirui Pan
To fill this gap, we review current state-of-the-art SSL methods for time series data in this article.
1 code implementation • NeurIPS 2023 • Hezhe Qiao, Guansong Pang
In this work, we explore this property to introduce a novel unsupervised anomaly scoring measure for GAD, local node affinity, that assigns a larger anomaly score to nodes that are less affiliated with their neighbors, with the affinity defined as similarity on node attributes/representations.
1 code implementation • CVPR 2023 • Haoyu Wang, Guansong Pang, Peng Wang, Lei Zhang, Wei Wei, Yanning Zhang
Few-shot open-set recognition (FSOR) is a challenging task of great practical value.
1 code implementation • ICCV 2023 • Tri Cao, Jiawen Zhu, Guansong Pang
Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data.
no code implementations • 15 Mar 2023 • Choubo Ding, Guansong Pang, Chunhua Shen
To this end, we propose a novel generic framework that can learn the domain features from the ID training samples by a dense prediction approach, with which different existing semantic-feature-based OOD detection methods can be seamlessly combined to jointly learn the in-distribution features from both the semantic and domain dimensions.
1 code implementation • 31 Jan 2023 • Chaoxi Niu, Guansong Pang, Ling Chen
To tackle this problem, this article proposes a novel approach that builds a discriminative model on collective affinity information (i. e., two sets of pairwise affinities between the negative instances and the anchor instance) to mine hard negatives in GCL.
1 code implementation • 17 Jan 2023 • Zhong Zhuang, Kai Ming Ting, Guansong Pang, Shuaibin Song
A treatment called Subgraph Centralization for graph anomaly detection is proposed to address all the above weaknesses.
no code implementations • ICCV 2023 • Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang
Motivated by the impressive generative and anti-noise capacity of diffusion model (DM), in this work, we introduce a novel DM-based method to predict the features of video frames for anomaly detection.
Ranked #8 on Anomaly Detection on UBnormal
1 code implementation • 2 Dec 2022 • Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie
In doing so, ACT effectively transfers anomaly-informed knowledge from the source graph to learn the complex node relations of the normal class for GAD on the target graph without any specification of the anomaly distributions.
1 code implementation • ICCV 2023 • Yuyuan Liu, Choubo Ding, Yu Tian, Guansong Pang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes.
Ranked #1 on Anomaly Detection on Fishyscapes (using extra training data)
1 code implementation • 25 Jul 2022 • Hongzuo Xu, Yijie Wang, Songlei Jian, Qing Liao, Yongjun Wang, Guansong Pang
Our one-class classifier is calibrated in two ways: (1) by adaptively penalizing uncertain predictions, which helps eliminate the impact of anomaly contamination while accentuating the predictions that the one-class model is confident in, and (2) by discriminating the normal samples from native anomaly examples that are generated to simulate genuine time series abnormal behaviors on the basis of original data.
2 code implementations • 14 Jun 2022 • Hongzuo Xu, Guansong Pang, Yijie Wang, Yongjun Wang
Isolation forest (iForest) has been emerging as arguably the most popular anomaly detector in recent years due to its general effectiveness across different benchmarks and strong scalability.
Ranked #1 on Anomaly Detection on NB15-DoS
1 code implementation • CVPR 2022 • Choubo Ding, Guansong Pang, Chunhua Shen
Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc.
Ranked #4 on Supervised Anomaly Detection on MVTec AD (using extra training data)
1 code implementation • 23 Mar 2022 • Yu Tian, Guansong Pang, Fengbei Liu, Yuyuan Liu, Chong Wang, Yuanhong Chen, Johan W Verjans, Gustavo Carneiro
Current polyp detection methods from colonoscopy videos use exclusively normal (i. e., healthy) training images, which i) ignore the importance of temporal information in consecutive video frames, and ii) lack knowledge about the polyps.
1 code implementation • 22 Mar 2022 • Yu Tian, Guansong Pang, Yuyuan Liu, Chong Wang, Yuanhong Chen, Fengbei Liu, Rajvinder Singh, Johan W Verjans, Mengyu Wang, Gustavo Carneiro
Our UAD approach, the memory-augmented multi-level cross-attentional masked autoencoder (MemMC-MAE), is a transformer-based approach, consisting of a novel memory-augmented self-attention operator for the encoder and a new multi-level cross-attention operator for the decoder.
1 code implementation • 19 Feb 2022 • Jitendra Singh Malik, Hezhe Qiao, Guansong Pang, Anton Van Den Hengel
Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media.
1 code implementation • 19 Dec 2021 • Rongrong Ma, Guansong Pang, Ling Chen, Anton Van Den Hengel
Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs.
3 code implementations • 24 Nov 2021 • Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro
However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems.
Ranked #2 on Anomaly Detection on Lost and Found (using extra training data)
2 code implementations • 3 Sep 2021 • Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro
Pre-training UAD methods with self-supervised learning, based on computer vision techniques, can mitigate this challenge, but they are sub-optimal because they do not explore domain knowledge for designing the pretext tasks, and their contrastive learning losses do not try to cluster the normal training images, which may result in a sparse distribution of normal images that is ineffective for anomaly detection.
1 code implementation • 1 Aug 2021 • Guansong Pang, Choubo Ding, Chunhua Shen, Anton Van Den Hengel
Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models.
Ranked #5 on Supervised Anomaly Detection on MVTec AD (using extra training data)
no code implementations • 30 Apr 2021 • Zhiyue Wu, Hongzuo Xu, Guansong Pang, Fengyuan Yu, Yijie Wang, Songlei Jian, Yongjun Wang
DRAM failure prediction is a vital task in AIOps, which is crucial to maintain the reliability and sustainable service of large-scale data centers.
no code implementations • 21 Mar 2021 • Guansong Pang, Longbing Cao, Ling Chen
Most of existing outlier detection methods assume that the outlier factors (i. e., outlierness scoring measures) of data entities (e. g., feature values and data objects) are Independent and Identically Distributed (IID).
1 code implementation • 5 Mar 2021 • Yu Tian, Guansong Pang, Fengbei Liu, Yuanhong Chen, Seon Ho Shin, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro
Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i. e., healthy) images to detect any abnormal (i. e., unhealthy) samples that do not conform to the expected normal patterns.
Ranked #1 on Anomaly Detection on LAG
3 code implementations • ICCV 2021 • Yu Tian, Guansong Pang, Yuanhong Chen, Rajvinder Singh, Johan W. Verjans, Gustavo Carneiro
To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos.
Anomaly Detection In Surveillance Videos Contrastive Learning +2
2 code implementations • 25 Jan 2021 • Yuanhong Chen, Yu Tian, Guansong Pang, Gustavo Carneiro
The adversarial interpolation is enforced to consistently learn a smooth Gaussian descriptor, even when the training data is small or contaminated with anomalous samples.
Ranked #2 on Anomaly Detection on MNIST (using extra training data)
no code implementations • ICCV 2021 • Cheng Yan, Guansong Pang, Lei Wang, Jile Jiao, Xuetao Feng, Chunhua Shen, Jingjing Li
In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i. e., an elevated view of an object from above.
no code implementations • ICCV 2021 • Cheng Yan, Guansong Pang, Jile Jiao, Xiao Bai, Xuetao Feng, Chunhua Shen
However, real-world ReID applications typically have highly diverse occlusions and involve a hybrid of occluded and non-occluded pedestrians.
no code implementations • 5 Dec 2020 • Guansong Pang, Ngoc Thien Anh Pham, Emma Baker, Rebecca Bentley, Anton Van Den Hengel
A wide variety of methods have been developed for identifying depression, but they focus primarily on measuring the degree to which individuals are suffering from depression currently.
no code implementations • 22 Sep 2020 • Cheng Yan, Guansong Pang, Xiao Bai, Jun Zhou, Lin Gu
The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches.
2 code implementations • 15 Sep 2020 • Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao
We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset.
no code implementations • 6 Jul 2020 • Guansong Pang, Chunhua Shen, Longbing Cao, Anton Van Den Hengel
This paper surveys the research of deep anomaly detection with a comprehensive taxonomy, covering advancements in three high-level categories and 11 fine-grained categories of the methods.
1 code implementation • 27 Mar 2020 • Jianpeng Zhang, Yutong Xie, Guansong Pang, Zhibin Liao, Johan Verjans, Wenxin Li, Zongji Sun, Jian He, Yi Li, Chunhua Shen, Yong Xia
In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into an one-class classification-based anomaly detection problem, and thus propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.
no code implementations • CVPR 2020 • Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Video anomaly detection is of critical practical importance to a variety of real applications because it allows human attention to be focused on events that are likely to be of interest, in spite of an otherwise overwhelming volume of video.
2 code implementations • 22 Dec 2019 • Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma
To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space.
no code implementations • 20 Nov 2019 • Cheng Yan, Guansong Pang, Xiao Bai, Chunhua Shen
The loss structures the augmented images resulted by the two types of image erasing in a two-level hierarchy and enforces multifaceted attention to different parts.
6 code implementations • 19 Nov 2019 • Guansong Pang, Chunhua Shen, Anton Van Den Hengel
Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e. g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail.
Ranked #1 on Network Intrusion Detection on NB15-Backdoor
3 code implementations • 30 Oct 2019 • Guansong Pang, Chunhua Shen, Huidong Jin, Anton Van Den Hengel
To detect both seen and unseen anomalies, we introduce a novel deep weakly-supervised approach, namely Pairwise Relation prediction Network (PReNet), that learns pairwise relation features and anomaly scores by predicting the relation of any two randomly sampled training instances, in which the pairwise relation can be anomaly-anomaly, anomaly-unlabeled, or unlabeled-unlabeled.
3 code implementations • 13 Jun 2018 • Guansong Pang, Longbing Cao, Ling Chen, Huan Liu
However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i. e., outliers).