Extreme Point Supervised Instance Segmentation

TL;DR

This paper presents a new instance segmentation method using extreme points that are easy to annotate, improving accuracy over existing box-supervised techniques by leveraging pseudo labels derived from these points.

Contribution

It introduces a novel approach that incorporates extreme points into pseudo label generation for improved box-supervised instance segmentation.

Findings

Outperforms existing box-supervised methods on three benchmarks.

Produces high-quality masks for multi-part objects.

Narrowing the gap with fully supervised methods.

Abstract

This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box annotation process while offering strong clues for precise segmentation, and thus allows to improve performance at the same annotation cost with box-supervised methods. Our work considers extreme points as a part of the true instance mask and propagates them to identify potential foreground and background points, which are all together used for training a pseudo label generator. Then pseudo labels given by the generator are in turn used for supervised learning of our final model. On three public benchmarks, our method significantly outperforms existing box-supervised methods, further narrowing the gap with its fully supervised counterpart. In particular, our model generates high-quality masks when a target object is separated into multiple parts, where previous box-supervised methods often fail.