Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations

TL;DR

This paper introduces TAPPS, a novel method for part-aware panoptic segmentation that jointly predicts object and part segments using shared queries, improving accuracy by aligning learning objectives with task goals.

Contribution

TAPPS is the first approach to jointly predict object and part segments with shared queries, directly linking parts to parent objects for better PPS performance.

Findings

TAPPS outperforms existing methods on PPS benchmarks.

Joint object-part prediction improves segmentation accuracy.

Achieves state-of-the-art PPS results.

Abstract

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However, their part-level predictions are not linked to individual parent objects. Therefore, their learning objective is not aligned with the PPS task objective, which harms the PPS performance. To solve this, and make more accurate PPS predictions, we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments, and (b) the part-level segments within those same objects. As a result, TAPPS learns to predict part-level segments that are linked to individual parent objects, aligning the learning objective with the task objective, and allowing TAPPS to leverage joint object-part representations. With experiments, we show that TAPPS considerably outperforms methods that predict objects and parts separately, and achieves new state-of-the-art PPS results.