Open-Set Semi-Supervised Object Detection

08/29/2022
by   Yen-Cheng Liu, et al.
15

Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain out-of-distribution (OOD) classes, which is unrealistic with larger-scale unlabeled datasets. In this paper, we consider a more practical yet challenging problem, Open-Set Semi-Supervised Object Detection (OSSOD). We first find the existing SSOD method obtains a lower performance gain in open-set conditions, and this is caused by the semantic expansion, where the distracting OOD objects are mispredicted as in-distribution pseudo-labels for the semi-supervised training. To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods. With the extensive studies, we found that leveraging an offline OOD detector based on a self-supervised vision transformer performs favorably against online OOD detectors due to its robustness to the interference of pseudo-labeling. In the experiment, our proposed framework effectively addresses the semantic expansion issue and shows consistent improvements on many OSSOD benchmarks, including large-scale COCO-OpenImages. We also verify the effectiveness of our framework under different OSSOD conditions, including varying numbers of in-distribution classes, different degrees of supervision, and different combinations of unlabeled sets.

READ FULL TEXT

page 2

page 7

page 19

research
05/23/2023

Online Open-set Semi-supervised Object Detection via Semi-supervised Outlier Filtering

Open-set semi-supervised object detection (OSSOD) methods aim to utilize...
research
07/28/2023

Semi-Supervised Object Detection in the Open World

Existing approaches for semi-supervised object detection assume a fixed ...
research
03/29/2021

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

In this paper, we delve into semi-supervised object detection where unla...
research
03/27/2018

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

Though quite challenging, leveraging large-scale unlabeled or partially ...
research
08/05/2021

Intelligent Railway Foreign Object Detection: A Semi-supervised Convolutional Autoencoder Based Method

Automated inspection and detection of foreign objects on railways is imp...
research
10/17/2022

Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving

Object detection for autonomous vehicles has received increasing attenti...
research
01/15/2020

Proposal Learning for Semi-Supervised Object Detection

In this paper, we focus on semi-supervised object detection to boost acc...

Please sign up or login with your details

Forgot password? Click here to reset