Open-World Object Detection via Discriminative Class Prototype Learning
- 16 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 626-630
Abstract
Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during training while identifying unseen classes, and 2) incrementally learn the knowledge of the identified unknown objects when the corresponding annotations is available. We propose a novel and efficient OWOD solution from a prototype perspective, which we call OCPL: Open-world object detection via discriminative Class Prototype Learning, which consists of a Proposal Embedding Aggregator (PEA), an Embedding Space Compressor (ESC) and a Cosine Similarity-based Classifier (CSC). All our proposed modules aim to learn the discriminative embeddings of known classes in the feature space to minimize the overlapping distributions of known and unknown classes, which is beneficial to differentiate known and unknown classes. Extensive experiments performed on PASCAL VOC and MS-COCO benchmark demonstrate the effectiveness of our proposed method.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- The Overlooked Elephant of Object Detection: Open Set2020
- FCOS: Fully Convolutional One-Stage Object Detection2019
- Zero-Shot Object Detection2018
- CosFace: Large Margin Cosine Loss for Deep Face Recognition2018
- Robust Classification with Convolutional Prototype Learning2018
- Dropout Sampling for Robust Object Detection in Open-Set Conditions2018
- Focal Loss for Dense Object Detection2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009