Deep Active Learning for Video-based Person Re-identification

12/14/2018
by   Menglin Wang, et al.
0

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.

READ FULL TEXT
research
12/26/2021

Unsupervised Clustering Active Learning for Person Re-identification

Supervised person re-identification (re-id) approaches require a large a...
research
04/21/2022

Towards Fewer Labels: Support Pair Active Learning for Person Re-identification

Supervised-learning based person re-identification (re-id) require a lar...
research
04/10/2020

Person Re-Identification via Active Hard Sample Mining

Annotating a large-scale image dataset is very tedious, yet necessary fo...
research
03/10/2022

Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection

Person Re-identification (Re-ID) has attracted great attention due to it...
research
04/22/2022

Label a Herd in Minutes: Individual Holstein-Friesian Cattle Identification

We describe a practically evaluated approach for training visual cattle ...
research
12/05/2016

Highly Efficient Regression for Scalable Person Re-Identification

Existing person re-identification models are poor for scaling up to larg...
research
08/25/2019

Learning adaptively from the unknown for few-example video person re-ID

This paper mainly studies one-example and few-example video person re-id...

Please sign up or login with your details

Forgot password? Click here to reset