Enhancing Object Discovery for Unsupervised Instance Segmentation and Object Detection

Xingyu Feng, Hebei Gao, Hong Li

Keywords: unsupervised learning, object discovery, pseudo labeling, zero-shot learning, normalized cut

TL;DR: We propose a novel and simple method to enhance object discovery in self-supervised models, enabling efficient multi-instance segmentation from a single image.

Abstract:

We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to learn
from these masks. CutOnce applies Normalized Cut only
once and does not rely on any clustering methods, but it
can generate multiple object masks in an image. We have
designed several novel yet simple modules that not only allow CutOnce to fully leverage the object discovery capabilities of self-supervised models, but also free it from reliance
on mask post-processing. During training, COLER achieves
strong performance without requiring specially designed loss
functions for pseudo labels, and its performance is further improved through self-training. COLER is a zero-shot unsupervised model that outperforms previous state-of-the-art methods on multiple benchmarks. We believe our method can help
advance the field of unsupervised object localization.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 7254