RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation

TL;DR

RankSeg introduces an adaptive segmentation framework that decomposes the task into multi-label classification and rank-adaptive pixel classification, improving performance across various segmentation tasks by focusing on relevant label subsets.

Contribution

The paper proposes a novel two-stage segmentation approach that dynamically selects relevant labels based on confidence scores, enhancing scalability and accuracy in large-category scenarios.

Findings

Achieved +0.8% on ADE20K panoptic segmentation

Achieved +0.7% on YouTubeVIS 2019 video instance segmentation

Achieved +0.7% on VSPW video semantic segmentation

Abstract

The segmentation task has traditionally been formulated as a complete-label pixel classification task to predict a class for each pixel from a fixed number of predefined semantic categories shared by all images or videos. Yet, following this formulation, standard architectures will inevitably encounter various challenges under more realistic settings where the scope of categories scales up (e.g., beyond the level of 1k). On the other hand, in a typical image or video, only a few categories, i.e., a small subset of the complete label are present. Motivated by this intuition, in this paper, we propose to decompose segmentation into two sub-problems: (i) image-level or video-level multi-label classification and (ii) pixel-level rank-adaptive selected-label classification. Given an input image or video, our framework first conducts multi-label classification over the complete label, then sorts the complete label and selects a small subset according to their class confidence scores. We then use a rank-adaptive pixel classifier to perform the pixel-wise classification over only the selected labels, which uses a set of rank-oriented learnable temperature parameters to adjust the pixel classifications scores. Our approach is conceptually general and can be used to improve various existing segmentation frameworks by simply using a lightweight multi-label classification head and rank-adaptive pixel classifier. We demonstrate the effectiveness of our framework with competitive experimental results across four tasks, including image semantic segmentation, image panoptic segmentation, video instance segmentation, and video semantic segmentation. Especially, with our RankSeg, Mask2Former gains +0.8%/+0.7%/+0.7% on ADE20K panoptic segmentation/YouTubeVIS 2019 video instance segmentation/VSPW video semantic segmentation benchmarks respectively.