A Unified Query-based Paradigm for Camouflaged Instance Segmentation

TL;DR

This paper introduces UQFormer, a unified query-based transformer framework that improves camouflaged instance segmentation and boundary detection by learning shared representations for accurate localization and segmentation.

Contribution

The paper proposes a novel unified query-based multi-task learning framework that integrates object region and boundary cues for camouflaged instance segmentation and boundary detection.

Findings

Outperforms 14 state-of-the-art methods in camouflaged instance segmentation

Effectively learns shared representations for segmentation and boundary detection

Significantly improves localization accuracy in camouflaged scenarios

Abstract

Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation. To this end, inspired by query-based transformers, we propose a unified query-based multi-task learning framework for camouflaged instance segmentation, termed UQFormer, which builds a set of mask queries and a set of boundary queries to learn a shared composed query representation and efficiently integrates global camouflaged object region and boundary cues, for simultaneous instance segmentation and instance boundary detection in camouflaged scenarios. Specifically, we design a composed query learning paradigm that learns a shared representation to capture object region and boundary features by the cross-attention interaction of mask queries and boundary queries in the designed multi-scale unified learning transformer decoder. Then, we present a transformer-based multi-task learning framework for simultaneous camouflaged instance segmentation and camouflaged instance boundary detection based on the learned composed query representation, which also forces the model to learn a strong instance-level query representation. Notably, our model views the instance segmentation as a query-based direct set prediction problem, without other post-processing such as non-maximal suppression. Compared with 14 state-of-the-art approaches, our UQFormer significantly improves the performance of camouflaged instance segmentation. Our code will be available at https://github.com/dongbo811/UQFormer.