Class-agnostic Object Detection

3 papers with code • 5 benchmarks • 5 datasets

Class-agnostic object detection aims to localize objects in images without specifying their categories.

Most implemented papers

Class-agnostic Object Detection with Multi-modal Transformer

mmaaz60/mvits_for_class_agnostic_od 22 Nov 2021

This has been a long-standing question in computer vision.

MOVE: Unsupervised Movable Object Segmentation and Detection

adambielski/move-seg 14 Oct 2022

We introduce MOVE, a novel method to segment objects without any form of supervision.

GOOD: Exploring Geometric Cues for Detecting Objects in an Open World

autonomousvision/good 22 Dec 2022

We address the task of open-world class-agnostic object detection, i. e., detecting every object in an image by learning from a limited number of base object classes.