Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite

TL;DR

This paper introduces CAMO++, a new dataset and benchmark suite for camouflaged instance segmentation in natural images, along with a novel fusion learning framework to enhance segmentation performance.

Contribution

The paper presents a significantly expanded dataset, a comprehensive benchmark, and a new fusion learning method for improved camouflaged instance segmentation.

Findings

State-of-the-art methods perform poorly on camouflaged instances.

The CFL framework improves segmentation accuracy over existing methods.

CAMO++ dataset enables more robust evaluation of camouflaged segmentation techniques.

Abstract

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths. We also provide a benchmark suite for the task of camouflaged instance segmentation. In particular, we present an extensive evaluation of state-of-the-art instance segmentation methods on our newly constructed CAMO++ dataset in various scenarios. We also present a camouflage fusion learning (CFL) framework for camouflaged instance segmentation to further improve the performance of state-of-the-art methods. The dataset, model, evaluation suite, and benchmark will be made publicly available on our project page: https://sites.google.com/view/ltnghia/research/camo_plus_plus