Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

• URL: http://arxiv.org/abs/2401.13551v1
• Date: Wed, 24 Jan 2024 16:11:42 GMT
• Title: Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
• Authors: Yongwei Nie, Hao Huang, Chengjiang Long, Qing Zhang, Pradipta Maji, Hongmin Cai
• Abstract summary: A typical Unsupervised Video Anomaly Detection (UVAD) method needs to train two models that generate pseudo labels for each other. We propose a novel interleaved framework that alternately trains a One-Class Classification (OCC) model and a Weakly-Supervised (WS) model for UVAD. Experiments demonstrate that the proposed UVAD method outperforms previous approaches.
• Score: 44.63919304001732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Without human annotations, a typical Unsupervised Video Anomaly Detection (UVAD) method needs to train two models that generate pseudo labels for each other. In previous work, the two models are closely entangled with each other, and it is not known how to upgrade their method without modifying their training framework significantly. Second, previous work usually adopts fixed thresholding to obtain pseudo labels, however the user-specified threshold is not reliable which inevitably introduces errors into the training process. To alleviate these two problems, we propose a novel interleaved framework that alternately trains a One-Class Classification (OCC) model and a Weakly-Supervised (WS) model for UVAD. The OCC or WS models in our method can be easily replaced with other OCC or WS models, which facilitates our method to upgrade with the most recent developments in both fields. For handling the fixed thresholding problem, we break through the conventional cognitive boundary and propose a weighted OCC model that can be trained on both normal and abnormal data. We also propose an adaptive mechanism for automatically finding the optimal threshold for the WS model in a loose to strict manner. Experiments demonstrate that the proposed UVAD method outperforms previous approaches.

Related papers

• CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels [13.807759089431855]
  Learning with noisy labels (LNL) poses a significant challenge in training a well-generalized model. Recent advances have achieved impressive performance by identifying clean labels and corrupted labels for training. We propose a novel optimal transport (OT) formulation, called Curriculum and Structure-aware Optimal Transport (CSOT)
  arXiv  Detail & Related papers  (2023-12-11T09:12:50Z)
• Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation [18.807921765977415]
  We propose a hard-aware instance adaptive self-training framework for UDA on the task of semantic segmentation. We develop a novel pseudo-label generation strategy with an instance adaptive selector. Experiments on GTA5 to Cityscapes, SYNTHIA to Cityscapes, and Cityscapes to Oxford RobotCar demonstrate the superior performance of our approach.
  arXiv  Detail & Related papers  (2023-02-14T11:52:26Z)
• Transductive CLIP with Class-Conditional Contrastive Learning [68.51078382124331]
  We propose Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch. A class-conditional contrastive learning mechanism is proposed to mitigate the reliance on pseudo labels. ensemble labels is adopted as a pseudo label updating strategy to stabilize the training of deep neural networks with noisy labels.
  arXiv  Detail & Related papers  (2022-06-13T14:04:57Z)
• A Lagrangian Duality Approach to Active Learning [119.36233726867992]
  We consider the batch active learning problem, where only a subset of the training data is labeled. We formulate the learning problem using constrained optimization, where each constraint bounds the performance of the model on labeled samples. We show, via numerical experiments, that our proposed approach performs similarly to or better than state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2022-02-08T19:18:49Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• Two-phase Pseudo Label Densification for Self-training based Domain Adaptation [93.03265290594278]
  We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD. In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images. In the second phase, we perform a confidence-based easy-hard classification. To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
  arXiv  Detail & Related papers  (2020-12-09T02:35:25Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)

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.