Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

• URL: http://arxiv.org/abs/2303.12369v1
• Date: Wed, 22 Mar 2023 08:11:22 GMT
• Title: Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
• Authors: Hui Lv, Zhongqi Yue, Qianru Sun, Bin Luo, Zhen Cui, Hanwang Zhang
• Abstract summary: Multiple Instance Learning (MIL) is prevailing in Weakly Supervised Video Anomaly Detection (WSVAD) We propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD.
• Score: 74.80595632328094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL.

Related papers

• Anomaly Detection by Context Contrasting [57.695202846009714]
  Anomaly detection focuses on identifying samples that deviate from the norm. Recent advances in self-supervised learning have shown great promise in this regard. We propose Con$$, which learns through context augmentations.
  arXiv  Detail & Related papers  (2024-05-29T07:59:06Z)
• Compact and De-biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image Classification [3.2721526745176144]
  We introduce a semi-supervision signal to de-bias the inter-slide variability and to capture the common factors of variation within normal patches. We evaluate our method on two public WSI datasets including Camelyon-16 and TCGA lung cancer.
  arXiv  Detail & Related papers  (2024-02-16T11:28:50Z)
• SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classification [2.3364474984323103]
  Multiple Instance Learning (MIL) has been widely used in weakly supervised whole slide image (WSI) classification. We propose a sparse coding MIL (SC-MIL) method that addresses the two aspects at the same time by leveraging sparse dictionary learning. The proposed SC module can be incorporated into any existing MIL framework in a plug-and-play manner with an acceptable computational cost.
  arXiv  Detail & Related papers  (2023-10-31T18:01:41Z)
• Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests [59.623267208433255]
  Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs. In this work, we examine five of the most prominent deep-MIL models and find that none of them respects the standard MIL assumption. We identify and demonstrate this problem via a proposed "algorithmic unit test", where we create synthetic datasets that can be solved by a MIL respecting model.
  arXiv  Detail & Related papers  (2023-10-27T03:05:11Z)
• Hard Nominal Example-aware Template Mutual Matching for Industrial Anomaly Detection [74.9262846410559]
  textbfHard Nominal textbfExample-aware textbfTemplate textbfMutual textbfMatching (HETMM) textitHETMM aims to construct a robust prototype-based decision boundary, which can precisely distinguish between hard-nominal examples and anomalies.
  arXiv  Detail & Related papers  (2023-03-28T17:54:56Z)
• Towards Open Set Video Anomaly Detection [11.944167192592905]
  Open Set Video Anomaly Detection (OpenVAD) aims to identify abnormal events from video data where both known anomalies and novel ones exist in testing. We develop a novel weakly supervised method for the OpenVAD problem by integrating evidential deep learning (EDL) and normalizing flows (NFs) into a multiple instance learning (MIL) framework.
  arXiv  Detail & Related papers  (2022-08-23T17:53:34Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction [52.94486705393062]
  We go beyond typical multi-instance learning (MIL) framework and propose a novel contrastive instance learning (CIL) framework. Specifically, we regard the initial MIL as the relational triple encoder and constraint positive pairs against negative pairs for each instance. Experiments demonstrate the effectiveness of our proposed framework, with significant improvements over the previous methods on NYT10, GDS and KBP.
  arXiv  Detail & Related papers  (2021-06-21T04:51:59Z)
• Weakly-supervised Video Anomaly Detection with Contrastive Learning of Long and Short-range Temporal Features [26.474395581531194]
  We propose a novel method, named Multi-scale Temporal Network trained with top-K Contrastive Multiple Instance Learning (MTN-KMIL) Our method outperforms several state-of-the-art methods by a large margin on three benchmark data sets.
  arXiv  Detail & Related papers  (2021-01-25T12:04:00Z)
• Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning [16.84711797934138]
  We address the challenging problem of whole slide image (WSI) classification. WSI classification can be cast as a multiple instance learning (MIL) problem when only slide-level labels are available. We propose a MIL-based method for WSI classification and tumor detection that does not require localized annotations.
  arXiv  Detail & Related papers  (2020-11-17T20:51:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.