MOVE: Unsupervised Movable Object Segmentation and DetectionDownload PDF

Published: 31 Oct 2022, Last Modified: 20 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Object Discovery, Saliency Detection, Object Segmentation, Object Detection, Self-Supervised Learning, Unsupervised Learning
TL;DR: SotA on unsupervised: saliency segmentation, object discovery and class-agnostic object detection
Abstract: We introduce MOVE, a novel method to segment objects without any form of supervision. MOVE exploits the fact that foreground objects can be shifted locally relative to their initial position and result in realistic (undistorted) new images. This property allows us to train a segmentation model on a dataset of images without annotation and to achieve state of the art (SotA) performance on several evaluation datasets for unsupervised salient object detection and segmentation. In unsupervised single object discovery, MOVE gives an average CorLoc improvement of 7.2% over the SotA, and in unsupervised class-agnostic object detection it gives a relative AP improvement of 53% on average. Our approach is built on top of self-supervised features (e.g. from DINO or MAE), an inpainting network (based on the Masked AutoEncoder) and adversarial training.
Supplementary Material: pdf
16 Replies