Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria

by   Keze Wang, et al.

Though quite challenging, the training of object detectors using large-scale unlabeled or partially labeled datasets has attracted increasing interests from researchers due to its fundamental importance for applications of neural networks and learning systems. To address this problem, many active learning (AL) methods have been proposed that employ up-to-date detectors to retrieve representative minority samples according to predefined confidence or uncertainty thresholds. However, these AL methods cause the detectors to ignore the remaining majority samples (i.e., those with low uncertainty or high prediction confidence). In this work, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effectively mining samples from these unlabeled majority data is key to training more powerful object detectors while minimizing user effort. Specifically, our ASM framework involves a selectively switchable sample selection mechanism for determining whether an unlabeled sample should be manually annotated via AL or automatically pseudo-labeled via a novel self-learning process. The proposed process can be compatible with mini-batch based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection. Extensive experiments on two public benchmarks clearly demonstrate that our ASM framework can achieve performance comparable to that of alternative methods but with significantly fewer annotations.


page 1

page 6

page 11

page 16

page 17


Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection

Though quite challenging, leveraging large-scale unlabeled or partially ...

Cost-Effective Active Learning for Deep Image Classification

Recent successes in learning-based image classification, however, heavil...

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification

This paper aims to develop a novel cost-effective framework for face ide...

ALWOD: Active Learning for Weakly-Supervised Object Detection

Object detection (OD), a crucial vision task, remains challenged by the ...

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

Object detectors usually achieve promising results with the supervision ...

Active Learning for Object Detection with Non-Redundant Informative Sampling

Curating an informative and representative dataset is essential for enha...

Ensemble of Part Detectors for Simultaneous Classification and Localization

Part-based representation has been proven to be effective for a variety ...

Please sign up or login with your details

Forgot password? Click here to reset