Towards Reducing Labeling Cost in Deep Object Detection

06/22/2021
by   Ismail Elezi, et al.
7

Deep neural networks have reached very high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the dependency on labels, various active-learning strategies have been proposed, typically based on the confidence of the detector. However, these methods are biased towards best-performing classes and can lead to acquired datasets that are not good representatives of the data in the testing set. In this work, we propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector, ensuring that the network performs accurately in all classes. Furthermore, our method is able to pseudo-label the very confident predictions, suppressing a potential distribution drift while further boosting the performance of the model. Experiments show that our method comprehensively outperforms a wide range of active-learning methods on PASCAL VOC07+12 and MS-COCO, having up to a 7.7 reduction in labeling cost.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2018

Active Learning for Deep Object Detection

The great success that deep models have achieved in the past is mainly o...
research
08/29/2022

Confidence Estimation for Object Detection in Document Images

Deep neural networks are becoming increasingly powerful and large and al...
research
03/30/2021

Active Learning for Deep Object Detection via Probabilistic Modeling

Active learning aims to reduce labeling costs by selecting only the most...
research
01/29/2019

Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector

Training a deep object detector for autonomous driving requires a huge a...
research
10/03/2021

Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm

Stream-based active learning (AL) is an efficient training data collecti...
research
02/26/2020

Streaming Active Deep Forest for Evolving Data Stream Classification

In recent years, Deep Neural Networks (DNNs) have gained progressive mom...
research
11/16/2021

Single Image Object Counting and Localizing using Active-Learning

The need to count and localize repeating objects in an image arises in d...

Please sign up or login with your details

Forgot password? Click here to reset