2.7k citations · 3.9k across the 41 of their papers we have counts for
21 papers · 1 filter
Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
Jiawen Zhu, Yew-Soon Ong, Chunhua Shen +1
Current zero-shot anomaly detection (ZSAD) methods show remarkable success in prompting large pre-trained vision-language models to detect anomalies in a target dataset without usi…
Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection
Jiawen Zhu, Choubo Ding, Yu Tian +1
Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen…
Unsupervised Recognition of Unknown Objects for Open-World Object Detection
Ruohuan Fang, Guansong Pang, Lei Zhou +2
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 a…
VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection
Peng Wu, Xuerong Zhou, Guansong Pang +4
The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful vis…
Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds
Tianqi Li, Guansong Pang, Xiao Bai +3
Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-worl…
Glocal Energy-based Learning for Few-Shot Open-Set Recognition
Haoyu Wang, Guansong Pang, Peng Wang +3
Few-shot open-set recognition (FSOR) is a challenging task of great practical value. It aims to categorize a sample to one of the pre-defined, closed-set classes illustrated by few…
Anomaly Detection under Distribution Shift
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. Most existing…
Improving Out-of-Distribution Detection with Disentangled Foreground and Background Features
Choubo Ding, Guansong Pang
Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn…
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Yuyuan Liu, Choubo Ding, Yu Tian +4
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on th…
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
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 appli…
Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection
Yu Tian, Guansong Pang, Fengbei Liu +5
Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images, which i) ignore the importance of temporal information in consecutiv…
Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
Rongrong Ma, Guansong Pang, Ling Chen +1
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.…
Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
Yu Tian, Yuyuan Liu, Guansong Pang +3
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external rec…
Explainable Deep Few-shot Anomaly Detection with Deviation Networks
Guansong Pang, Choubo Ding, Chunhua Shen +1
Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue…
Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images
Yu Tian, Guansong Pang, Fengbei Liu +5
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 confor…
Deep One-Class Classification via Interpolated Gaussian Descriptor
Yuanhong Chen, Yu Tian, Guansong Pang +1
One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data descript…
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
Yu Tian, Guansong Pang, Yuanhong Chen +3
Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing a…
Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
Cheng Yan, Guansong Pang, Xiao Bai +2
Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key…
Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
Guansong Pang, Cheng Yan, Chunhua Shen +2
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 int…
Unsupervised Representation Learning by Predicting Random Distances
Hu Wang, Guansong Pang, Chunhua Shen +1
Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensiona…
Unified Multifaceted Feature Learning for Person Re-Identification
Cheng Yan, Guansong Pang, Xiao Bai +1
Person re-identification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras, of which it is of great importance to learn multifaceted features…