Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
This addresses the problem of segmenting objects in unseen categories for computer vision applications, representing a novel method rather than an incremental improvement.
The paper tackles open-world instance segmentation by proposing Generic Grouping Networks (GGNs) that use learned pairwise pixel affinities to generate pseudo-ground-truth masks without semantic supervision, achieving state-of-the-art performance on benchmarks like COCO, LVIS, ADE20K, and UVO.
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled datasets, and out-of-domain evaluation performance drops significantly. Here we propose a novel approach for mask proposals, Generic Grouping Networks (GGNs), constructed without semantic supervision. Our approach combines a local measure of pixel affinity with instance-level mask supervision, producing a training regimen designed to make the model as generic as the data diversity allows. We introduce a method for predicting Pairwise Affinities (PA), a learned local relationship between pairs of pixels. PA generalizes very well to unseen categories. From PA we construct a large set of pseudo-ground-truth instance masks; combined with human-annotated instance masks we train GGNs and significantly outperform the SOTA on open-world instance segmentation on various benchmarks including COCO, LVIS, ADE20K, and UVO. Code is available on project website: https://sites.google.com/view/generic-grouping/.