# Deep Active Learning for Video-based Person Re-identification

arXiv: https://arxiv.org/abs/1812.05785 · HTML: https://mlsanity.com/paper/1812.05785/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2018.

## Built on by (most cited first, 4 of 4)

- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [Label a Herd in Minutes: Individual Holstein-Friesian Cattle Identification](https://mlsanity.com/paper/2204.10905/) (2022)
- [Deep Learning for Video-based Person Re-Identification: A Survey](https://mlsanity.com/paper/2303.11332/) (2023)
- [AL-GTD: Deep Active Learning for Gaze Target Detection](https://mlsanity.com/paper/2409.18561/) (2024)

## Abstract (arXiv)

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.