Name
Title | ||
|---|---|---|
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity |
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/CVPR52688.2022.00438 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Segmentation,grouping and shape analysis, Recognition: detection,categorization,retrieval | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wei-Yao Wang | 1 | 0 | 0.68 |
| Matt Feiszli | 2 | 0 | 0.34 |
| Heng Wang | 3 | 2792 | 82.10 |
| Jitendra Malik | 4 | 39445 | 3782.10 |
| Du Tran | 5 | 1289 | 38.35 |