COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image Understanding

TL;DR

This paper introduces COCO-OLAC, a large-scale occlusion-labeled dataset for panoptic segmentation, and demonstrates how occlusion impacts model performance, proposing a contrastive learning method to improve robustness under occlusion.

Contribution

The paper provides a new dataset with occlusion labels and a contrastive learning approach to enhance model robustness against occlusion in segmentation tasks.

Findings

Occlusion significantly degrades panoptic segmentation performance.

The proposed contrastive learning method improves robustness to occlusion.

Achieves state-of-the-art results on the COCO-OLAC dataset.

Abstract

To help address the occlusion problem in panoptic segmentation and image understanding, this paper proposes a new large-scale dataset named COCO-OLAC (COCO Occlusion Labels for All Computer Vision Tasks), which is derived from the COCO dataset by manually labelling images into three perceived occlusion levels. Using COCO-OLAC, we systematically assess and quantify the impact of occlusion on panoptic segmentation on samples having different levels of occlusion. Comparative experiments with SOTA panoptic models demonstrate that the presence of occlusion significantly affects performance, with higher occlusion levels resulting in notably poorer performance. Additionally, we propose a straightforward yet effective method as an initial attempt to leverage the occlusion annotation using contrastive learning to render a model that learns a more robust representation capturing different severities of occlusion. Experimental results demonstrate that the proposed approach boosts the performance of the baseline model and achieves SOTA performance on the proposed COCO-OLAC dataset.