FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter

TL;DR

This paper introduces FAPIS, a novel few-shot, anchor-free, part-based instance segmentation method that models shared latent object parts to improve segmentation of unseen classes, outperforming existing methods on COCO-20i.

Contribution

The paper presents a new few-shot, anchor-free, part-based instance segmenter that explicitly models shared object parts to enhance generalization to new classes.

Findings

Significantly outperforms state-of-the-art on COCO-20i

Effective explicit modeling of shared object parts

Improved few-shot instance segmentation performance

Abstract

This paper is about few-shot instance segmentation, where training and test image sets do not share the same object classes. We specify and evaluate a new few-shot anchor-free part-based instance segmenter FAPIS. Our key novelty is in explicit modeling of latent object parts shared across training object classes, which is expected to facilitate our few-shot learning on new classes in testing. We specify a new anchor-free object detector aimed at scoring and regressing locations of foreground bounding boxes, as well as estimating relative importance of latent parts within each box. Also, we specify a new network for delineating and weighting latent parts for the final instance segmentation within every detected bounding box. Our evaluation on the benchmark COCO-20i dataset demonstrates that we significantly outperform the state of the art.