Deep Active Learning for Video-based Person Re-identification
It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deployment. How to maximally reduce the annotation cost while retaining the re-ID performance becomes an interesting problem. In this paper, we address this problem by integrating an active learning scheme into a deep learning framework. Noticing that the truly matched tracklet-pairs, also denoted as true positives (TP), are the most informative samples for our re-ID model, we propose a sampling criterion to choose the most TP-likely tracklet-pairs for annotation. A view-aware sampling strategy considering view-specific biases is designed to facilitate candidate selection, followed by an adaptive resampling step to leave out the selected candidates that are unnecessary to annotate. Our method learns the re-ID model and updates the annotation set iteratively. The re-ID model is supervised by the tracklets' pesudo labels that are initialized by treating each tracklet as a distinct class. With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model. While being simple, the proposed method demonstrates its effectiveness on three video-based person re-ID datasets. Experimental results show that less than 3\% pairwise annotations are needed for our method to reach comparable performance with the fully-supervised setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningPerson Re-IdentificationVideo-Based Person Re-IdentificationSimilar Papers 제목 키워드 기반
Learning Person Re-identification Models from Videos with Weak Supervision
Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the s…
Multiple Instance LearningPerson Re-IdentificationVideo-Based Person Re-IdentificationiQIYI-VID: A Large Dataset for Multi-modal Person Identification
Person identification in the wild is very challenging due to great variation in poses, face quality, clothes, makeup and so on. Traditional research, such as face recognition, person re-identification, and speaker recogn…
Face RecognitionMulti-Modal Person IdentificationPerson IdentificationPerson Re-Identification+1EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams
Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users. While emerging benchmarks address proactivity, they are largely conf…
Intent RecognitionConvolutional Temporal Attention Model for Video-based Person Re-identification
The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to f…
Person Re-IdentificationSemantic SegmentationVideo-Based Person Re-IdentificationOpen-set Person Re-identification
Person re-identification is becoming a hot research for developing both machine learning algorithms and video surveillance applications. The task of person re-identification is to determine which person in a gallery has …
Metric LearningPerson Re-Identification