Name
Abstract | ||
|---|---|---|
While object part segmentation is useful for many applications, typical approaches require a large amount of labeled data to train a model for good performance. To reduce the labeling effort, weak supervision cues such as object keypoints have been used to generate pseudo-part annotations which can subsequently be used to train larger models. However, previous weakly-supervised part segmentation methods require the same object classes during both training and testing. We propose a new model to use keypoint guidance for segmenting parts of novel object classes given that they have similar structures as seen objects - different types of four-legged animals, for example. We show that a non-parametric template matching approach is more effective than pixel classification for part segmentation, especially for small or less frequent parts. To evaluate the generalizability of our approach, we introduce two new datasets that contain 200 quadrupeds in total with both keypoint and part segmentation annotations. We show that our approach can outperform existing models by a large margin on the novel object part segmentation task using limited part segmentation labels during training. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/WACV48630.2021.00178 | 2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021) |
DocType | ISSN | Citations |
Conference | 2472-6737 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shujon Naha | 1 | 0 | 0.34 |
| Qingyang Xiao | 2 | 52 | 4.80 |
| Prianka Banik | 3 | 0 | 0.68 |
| Md. Alimoor Reza | 4 | 9 | 4.21 |
| David J. Crandall | 5 | 0 | 0.34 |