Detect unknown objects using unsupervised region proposal methods with MEPU


Detect unknown objects using unsupervised region proposal methods with MEPU

Unsupervised Recognition of Unknown Objects for Open-World Object Detection
arXiv paper abstract
arXiv PDF paper

Open-World Object Detection (OWOD) … is … detecting both known and unknown objects and incrementally learning newly introduced knowledge.

Current … models … focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects.

While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background.

… this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods.

The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions.

… method … significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes …

Stay up to date. Subscribe to my posts
Web site with my other posts by category


Photo by Cater Yang on Unsplash



AI News Clips by Morris Lee: News to help your R&D

A computer vision consultant in artificial intelligence and related hitech technologies 37+ years. Am innovator with 66+ patents and ready to help a firm's R&D.