Related papers: Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

URL: http://arxiv.org/abs/2211.15597v4
Date: Wed, 17 Jul 2024 16:01:00 GMT
Title: Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
Authors: Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah,
Abstract summary: We propose a very fast frame-level model for anomaly detection in video. It learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. Our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS.
Score: 106.42167050921718
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fastest competing method, and between 28 and 62 times faster than object-centric models, while obtaining comparable results to recent methods. Our evaluation also indicates that our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS. In addition, we carry out a comprehensive ablation study to justify our architectural design choices. Our code is freely available at: https://github.com/ristea/fast-aed.

Related papers

Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices [5.696239274365031]
We propose a novel strategy by incorporating knowledge distillation and model pruning to overcome the inherent trade-off between speed and accuracy. We obtained a model that maintains real-time performance while delivering high accuracy on edge devices.
arXiv Detail & Related papers (2024-05-20T06:03:55Z)
Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors [117.61449210940955]
We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. We introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. We generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames.
arXiv Detail & Related papers (2023-06-21T06:18:05Z)
Anomaly Detection via Multi-Scale Contrasted Memory [3.0170109896527086]
We introduce a new two-stage anomaly detector which memorizes during training multi-scale normal prototypes to compute an anomaly deviation score. Our model highly improves the state-of-the-art performance on a wide range of object, style and local anomalies with up to 35% error relative improvement on CIFAR-10.
arXiv Detail & Related papers (2022-11-16T16:58:04Z)
Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors [17.386735294534738]
We propose a Descriptor Distillation framework for local descriptor learning, called DesDis. A student model gains knowledge from a pre-trained teacher model, and it is further enhanced via a designed teacher-student regularizer. Experimental results on 3 public datasets demonstrate that the equal-weight student models could achieve significantly better performances than their teachers.
arXiv Detail & Related papers (2022-09-23T18:22:04Z)
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection [108.57862846523858]
We revisit the self-supervised multi-task learning framework, proposing several updates to the original method. We modernize the 3D convolutional backbone by introducing multi-head self-attention modules. In our attempt to further improve the model, we study additional self-supervised learning tasks, such as predicting segmentation maps.
arXiv Detail & Related papers (2022-07-16T19:25:41Z)
When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
arXiv Detail & Related papers (2021-05-27T13:51:42Z)
Is Space-Time Attention All You Need for Video Understanding? [50.78676438502343]
We present a convolution-free approach to built exclusively on self-attention over space and time. "TimeSformer" adapts the standard Transformer architecture to video by enabling feature learning from a sequence of frame-level patches. TimeSformer achieves state-of-the-art results on several major action recognition benchmarks.
arXiv Detail & Related papers (2021-02-09T19:49:33Z)
Distilling Object Detectors with Task Adaptive Regularization [97.52935611385179]
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
arXiv Detail & Related papers (2020-06-23T15:58:22Z)

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