Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSensing Anomalies like Humans: A Hominine Framework to Detect Abnormal Events from Unlabeled Videos
73
0
0.0
(
0
)
Added by
Guang Yu
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Video anomaly detection (VAD) has constantly been a vital topic in video analysis. As anomalies are often rare, it is typically addressed under a semi-supervised setup, which requires a training set with pure normal videos. To avoid exhausted manual labeling, we are inspired by how humans sense anomalies and propose a hominine framework that enables both unsupervised and end-to-end VAD. The framework is based on two key observations: 1) Human perception is usually local, i.e. focusing on local foreground and its context when sensing anomalies. Thus, we propose to impose locality-awareness by localizing foreground with generic knowledge, and a region localization strategy is designed to exploit local context. 2) Frequently-occurred events will mould humans definition of normality, which motivates us to devise a surrogate training paradigm. It trains a deep neural network (DNN) to learn a surrogate task with unlabeled videos, and frequently-occurred events will play a dominant role in moulding the DNN. In this way, a training loss gap will automatically manifest rarely-seen novel events as anomalies. For implementation, we explore various surrogate tasks as well as both classic and emerging DNN models. Extensive evaluations on commonly-used VAD benchmarks justify the frameworks applicability to different surrogate tasks or DNN models, and demonstrate its astonishing effectiveness: It not only outperforms existing unsupervised solutions by a wide margin (8% to 10% AUROC gain), but also achieves comparable or even superior performance to state-of-the-art semi-supervised counterparts.
rate research
Read More
In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal variation exploitation, and online update, are the central causes of the performance bottleneck of existing unsupervised trackers. To narrow the gap between unsupervised trackers and supervised counterparts, we propose an effective unsupervised learning approach composed of three stages. First, we sample sequentially moving objects with unsupervised optical flow and dynamic programming, instead of random cropping. Second, we train a naive Siamese tracker from scratch using single-frame pairs. Third, we continue training the tracker with a novel cycle memory learning scheme, which is conducted in longer temporal spans and also enables our tracker to update online. Extensive experiments show that the proposed USOT learned from unlabeled videos performs well over the state-of-the-art unsupervised trackers by large margins, and on par with recent supervised deep trackers. Code is available at https://github.com/VISION-SJTU/USOT.
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data. We introduce a unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities. Our approach can help advance understanding of visual patterns in VOS and significantly reduce annotation burden. With a carefully-designed architecture and strong representation learning ability, our learned model can be applied to diverse VOS settings, including object-level zero-shot VOS, instance-level zero-shot VOS, and one-shot VOS. Experiments demonstrate promising performance in these settings, as well as the potential of MuG in leveraging unlabeled data to further improve the segmentation accuracy.
Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmente
Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper proposes a self-supervised training framework that learns a common multimodal embedding space that, in addition to sharing representations across different modalities, enforces a grouping of semantically similar instances. To this end, we extend the concept of instance-level contrastive learning with a multimodal clustering step in the training pipeline to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains. To evaluate our approach, we train our model on the HowTo100M dataset and evaluate its zero-shot retrieval capabilities in two challenging domains, namely text-to-video retrieval, and temporal action localization, showing state-of-the-art results on four different datasets.
Static image action recognition, which aims to recognize action based on a single image, usually relies on expensive human labeling effort such as adequate labeled action images and large-scale labeled image dataset. In contrast, abundant unlabeled videos can be economically obtained. Therefore, several works have explored using unlabeled videos to facilitate image action recognition, which can be categorized into the following two groups: (a) enhance visual representations of action images with a designed proxy task on unlabeled videos, which falls into the scope of self-supervised learning; (b) generate auxiliary representations for action images with the generator learned from unlabeled videos. In this paper, we integrate the above two strategies in a unified framework, which consists of Visual Representation Enhancement (VRE) module and Motion Representation Augmentation (MRA) module. Specifically, the VRE module includes a proxy task which imposes pseudo motion label constraint and temporal coherence constraint on unlabeled videos, while the MRA module could predict the motion information of a static action image by exploiting unlabeled videos. We demonstrate the superiority of our framework based on four benchmark human action datasets with limited labeled data.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
