Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

2024-01-01 · CVPR 2024 1 · Junxi Chen, Liang Li, Li Su, Zheng-Jun Zha, Qingming Huang

Weakly-supervised Video Anomaly Detection (wVAD) aims to detect frame-level anomalies using only video-level labels in training. Due to the limitation of coarse-grained labels Multi-Instance Learning (MIL) is prevailing in wVAD. However MIL suffers from insufficiency of binary supervision to model diverse abnormal patterns. Besides the coupling between abnormality and its context hinders the learning of clear abnormal event boundary. In this paper we propose prompt-enhanced MIL to detect various abnormal events while ensuring clear event boundaries. Concretely we design the abnormal-aware prompts by using abnormal class annotations together with learnable prompt which can incorporate semantic priors into video features dynamically. The detector can utilize the semantic-rich features to capture diverse abnormal patterns. In addition normal context prompt is introduced to amplify the distinction between abnormality and its context facilitating the generation of clear boundary. With the mutual enhancement of abnormal-aware and normal context prompt the model can construct discriminative representations to detect divergent anomalies without ambiguous event boundaries. Extensive experiments demonstrate our method achieves SOTA performance on three public benchmarks. The code is available at https://github.com/Junxi-Chen/PE-MIL.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection Multiple Instance Learning Video Anomaly Detection Weakly-supervised Video Anomaly Detection

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection

2023-06-26 · Yujiang Pu, Xiaoyu Wu, Lulu Yang, Shengjin Wang

Video anomaly detection under weak supervision presents significant challenges, particularly due to the lack of frame-level annotations during training. While prior research has utilized graph convolution networks and se…

Anomaly Detection Anomaly Detection In Surveillance Videos Video Anomaly Detection Weakly-supervised Anomaly Detection+1

Contrastive Multiple Instance Learning for Weakly Supervised Person ReID

2024-02-12 · Jacob Tyo, Zachary C. Lipton

The acquisition of large-scale, precisely labeled datasets for person re-identification (ReID) poses a significant challenge. Weakly supervised ReID has begun to address this issue, although its performance lags behind f…

Multiple Instance Learning Person Re-Identification

WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels

2025-01-01 · CVPR 2025 1 · Hyeokjun Kweon, Kuk-Jin Yoon

Instance segmentation traditionally relies on dense pixel-level annotations, making it costly and labor-intensive. To alleviate this burden, weakly supervised instance segmentation utilizes cost-effective weak labels…

Instance Segmentation Segmentation Semantic Segmentation Weakly-supervised instance segmentation

TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification

2023-05-01 · Litao Yang, Deval Mehta, Sidong Liu, Dwarikanath Mahapatra 외

Digital pathology based on whole slide images (WSIs) plays a key role in cancer diagnosis and clinical practice. Due to the high resolution of the WSI and the unavailability of patch-level annotations, WSI classification…

image-classification Image Classification Multiple Instance Learning whole slide images

Multiple Instance Detection Network with Online Instance Classifier Refinement

2017-04-01 · CVPR 2017 7 · Peng Tang, Xinggang Wang, Xiang Bai, Wenyu Liu

Of late, weakly supervised object detection is with great importance in object recognition. Based on deep learning, weakly supervised detectors have achieved many promising results. However, compared with fully supervise…

Multiple Instance Learning Object object-detection Object Detection+2