Learning to Adapt to Unseen Abnormal Activities under Weak Supervision

30/11/2020

Learning to Adapt to Unseen Abnormal Activities under Weak Supervision

JaeYoo Park, Junha Kim, Bohyung Han

Keywords:

Abstract Paper Similar Papers

Abstract: We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when only video-level annotations of binary labels are available.Our work is motivated by the fact that existing methods suffer from poor generalization to diverse unseen examples.We claim that an anomaly detector equipped with a meta-learning scheme alleviates the limitation by leading the model to an initialization point for better optimization.We evaluate the performance of our framework on two challenging datasets, UCF-Crime and ShanghaiTech. The experimental results demonstrate that our algorithm boosts the capability to localize unseen abnormal events in a weakly supervised setting.Besides the technical contributions, we perform the annotation of missing labels in the UCF-Crime dataset and make our task evaluated effectively.

The video of this talk cannot be embedded. You can watch it here:

https://accv2020.github.io/miniconf/poster_479.html

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

19/08/2021

Understanding the Effect of Bias in Deep Anomaly Detection

Ziyu Ye, Yuxin Chen, Haitao Zheng

Keywords Paper

Machine Learning, Deep Learning, Anomaly/Outlier Detection, Semi-Supervised Learning

0

0

0

1

14:23

06/12/2020

Restoring Negative Information in Few-Shot Object Detection

Yukuan Yang, Fangyun Wei, Miaojing Shi, Guoqi Li

Keywords Paper

0

0

0

0

3:24

14/06/2020

Noise-Aware Fully Webly Supervised Object Detection

Yunhang Shen, Rongrong Ji, Zhiwei Chen and
Xiaopeng Hong, Feng Zheng, Jianzhuang Liu, Mingliang Xu, Qi Tian

Keywords Paper

webly supervised object detection, weakly supervised object detection, object detection

0

0

0

0

1:01

19/08/2021

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

Haoqing Wang, Zhi-Hong Deng

Keywords Paper

Computer Vision, Recognition, Adversarial Machine Learning, Deep Learning

0

0

0

0

10:39

06/12/2020

Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation

Ping Hu, Stan Sclaroff, Kate Saenko

Keywords Paper

0

0

0

0

3:24

14/06/2020

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis and
Kyle Genova, Prem Nair, Kenji Hata, Olga Russakovsky

Keywords Paper

fairness, bias mitigation, recognition, domain shift, adversarial training

0

0

0

0

1:01

03/05/2021

Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples

Ziang Yan, Yiwen Guo, Jian Liang, Changshui Zhang

Keywords Paper

hard-label attack, adversarial attack, black-box attack, reinforcement learning

0

0

0

0

4:55

06/12/2021

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

Zhenyu Wang, Ya-Li Li, Ye Guo, Shengjin Wang

Keywords Paper

machine learning, vision, semi-supervised learning

0

0

0

0

7:12

02/02/2021

Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning

Syed Zawad, Ahsan Ali, Pin-Yu Chen and
Ali Anwar, Yi Zhou, Nathalie Baracaldo, Yuan Tian, Feng Yan

Keywords Paper

0

0

0

0

19:26

19/08/2021

RCA: A Deep Collaborative Autoencoder Approach for Anomaly Detection

Boyang Liu, Ding Wang, Kaixiang Lin and
Pang-Ning Tan, Jiayu Zhou

Keywords Paper

Data Mining, Anomaly/Outlier Detection, Unsupervised Learning

0

0

0

0

12:05

22/11/2021

Simpler Does It: Generating Semantic Labels with Objectness Guidance

Md Amirul Islam, Matthew Kowal, Sen Jia and
Konstantinos Derpanis, Neil Bruce

Keywords Paper

Weakly supervised segmentation, semi supervised segmentation, Pseudo-label generation, Class Activation Maps, Objectness, Saliency

0

0

0

0

3:02

05/01/2021

Few-Shot Learning via Feature Hallucination With Variational Inference

Qinxuan Luo, Lingfeng Wang, Jingguo Lv and
Shiming Xiang, Chunhong Pan

Keywords Paper

0

0

0

0

4:56

06/12/2021

STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data

Zhi Zhou, Lan-Zhe Guo, Zhanzhan Cheng and
Yu-Feng Li, Shiliang Pu

Keywords Paper

optimization, semi-supervised learning

0

0

0

0

11:24

19/08/2021

Masked Contrastive Learning for Anomaly Detection

Hyunsoo Cho, Jinseok Seol, Sang-goo Lee

Keywords Paper

Data Mining, Anomaly/Outlier Detection, Clustering, Clustering

0

0

0

0

14:12

05/01/2021

PNPDet: Efficient Few-Shot Detection Without Forgetting via Plug-and-Play Sub-Networks

Gongjie Zhang, Kaiwen Cui, Rongliang Wu and
Shijian Lu, Yonghong Tian

Keywords Paper

0

0

0

0

5:01

14/06/2020

Attack to Explain Deep Representation

Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian

Keywords Paper

interpreting deep learning, adversarial attack, explanation attack, explainable ai, image generation

0

0

0

0

1:01

02/02/2021

Few-Shot One-Class Classification via Meta-Learning

Ahmed Frikha, Denis Krompaß, Hans-Georg Köpken, Volker Tresp

Keywords Paper

0

0

0

0

18:43

14/06/2020

PatchVAE: Learning Local Latent Codes for Recognition

Kamal Gupta, Saurabh Singh, Abhinav Shrivastava

Keywords Paper

unsupervised, vae, self-supervised, generative, mid-level patches, variational auto-encoder, representation learning, autoencoder, part mining, patchvae

0

1

1

1

1:01

05/01/2021

Detecting Human-Object Interaction With Mixed Supervision

Suresh Kirthi Kumaraswamy, Miaojing Shi, Ewa Kijak

Keywords Paper

0

0

0

0

4:57

06/12/2020

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

Wei-An Lin, Chun Pong Lau, Alexander Levine and
Rama Chellappa, Soheil Feizi

Keywords Paper

0

0

0

0

3:24

02/02/2021

Learning to Purify Noisy Labels via Meta Soft Label Corrector

Yichen Wu, Jun Shu, Qi Xie and
Qian Zhao, Deyu Meng

Keywords Paper

0

0

0

0

13:01

06/12/2021

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

Nicklas Hansen, Hao Su, Xiaolong Wang

Keywords Paper

reinforcement learning and planning, transformers

0

0

0

0

8:43

02/02/2021

Improving Sample Efficiency in Model-Free Reinforcement Learning from Images

Denis Yarats, Amy Zhang, Ilya Kostrikov and
Brandon Amos, Joelle Pineau, Rob Fergus

Keywords Paper

0

0

0

0

12:19

05/01/2021

Towards Visually Explaining Video Understanding Networks With Perturbation

Zhenqiang Li, Weimin Wang, Zuoyue Li and
Yifei Huang, Yoichi Sato

Keywords Paper

0

0

0

0

4:53

06/12/2020

VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain

Jinsung Yoon, Yao Zhang, James Jordon, Mihaela van der Schaar

Keywords Paper

0

0

0

0

3:25

02/02/2021

Explainable Models with Consistent Interpretations

Vipin Pillai, Hamed Pirsiavash

Keywords Paper

0

0

0

0

16:20

18/07/2021

PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees

Jonas Rothfuss, Vincent Fortuin, Martin Josifoski, Andreas Krause

Keywords Paper

Algorithms, Multitask, Transfer, and Meta Learning

1

1

0

0

5:46

14/06/2020

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

Bo Pang, Yizhuo Li, Yifan Zhang and
Muchen Li, Cewu Lu

Keywords Paper

bounding-tube, mot, one-stage, tube-nms, fcn

0

0

0

0

4:55

02/02/2021

Weakly-supervised Temporal Action Localization by Uncertainty Modeling

Pilhyeon Lee, Jinglu Wang, Yan Lu, Hyeran Byun

Keywords Paper

0

0

0

0

14:01

05/01/2021

Where to Look?: Mining Complementary Image Regions for Weakly Supervised Object Localization

Sadbhavana Babar, Sukhendu Das

Keywords Paper

0

0

0

0

5:01

22/11/2021

Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix

Ziqi Zhang, Yuexiang Li, Hongxin Wei and
Kai Ma, Tao Xu, Yefeng Zheng

Keywords Paper

noisy labels, image classification, instance selection, robust learning, inter-class correlation, soft label, medical image

0

0

0

0

2:52

06/12/2020

Adversarial Self-Supervised Contrastive Learning

Minseon Kim, Jihoon Tack, Sung Ju Hwang

Keywords Paper

0

0

0

0

3:19

07/09/2020

Meta-RetinaNet for Few-shot Object Detection

Shaoqi Li, Wenfeng Song, Shuai Li and
Aimin Hao, Hong Qin

Keywords Paper

Few shot, object detection, meta-learning, Meta-RetinaNet, Balanced Loss, coefficient vector

0

0

0

0

8:51

02/02/2021

A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation

Ervine Zheng, Qi Yu, Rui Li and
Pengcheng Shi, Anne Haake

Keywords Paper

0

0

0

0

14:21

18/07/2021

Emphatic Algorithms for Deep Reinforcement Learning

Ray Jiang, Tom Zahavy, Zhongwen Xu and
Adam White, Matteo Hessel, Charles Blundell, Hado van Hasselt

Keywords Paper

Reinforcement Learning and Planning, Deep RL

1

0

0

0

5:21

26/04/2020

Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents

Christian Rupprecht, Cyril Ibrahim, Christopher J. Pal

Keywords Paper

Visualization, Reinforcement Learning, Safety

0

0

0

0

4:52

06/12/2021

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

Mi Luo, Fei Chen, Dapeng Hu and
Yifan Zhang, Jian Liang, Jiashi Feng

Keywords Paper

optimization, machine learning, federated learning

0

0

0

0

3:27

14/06/2020

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

Sven Gowal, Chongli Qin, Po-Sen Huang and
Taylan Cemgil, Krishnamurthy Dvijotham, Timothy Mann, Pushmeet Kohli

Keywords Paper

real-world robustness, adversarial examples, disentangled latents, generative models, spurious correlations

0

0

0

0

1:01

04/07/2020

What is Learned in Visually Grounded Neural Syntax Acquisition

Noriyuki Kojima, Hadar Averbuch-Elor, Alexander Rush, Yoav Artzi

Keywords Paper

Visually Acquisition, bootstrap models, blackbox models, visual components

0

0

0

0

6:41

26/04/2020

Revisiting Self-Training for Neural Sequence Generation

Junxian He, Jiatao Gu, Jiajun Shen, Marc'Aurelio Ranzato

Keywords Paper

self-training, semi-supervised learning, neural sequence generatioin

0

0

0

0

5:07