Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.13582 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910654510661632 |
|---|---|
| author | Ypsilantis, Nikolaos-Antonios Chum, Ondřej |
| author_facet | Ypsilantis, Nikolaos-Antonios Chum, Ondřej |
| contents | This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are exploited: ImageNet classification-trained ViT, whose features are used to estimate rough object localization through intra-class token relevance, and a self-supervised DINO-ViT for intra-image token relevance. On recent challenging benchmarks, the method achieves state-of-the-art performance among methods trained with the same level of supervision (image labels) while being competitive with methods trained with pixel-level supervision (binary masks). The benefits of the proposed co-segmentation method are further demonstrated in the task of large-scale sketch recognition, that is, the classification of sketches into a wide range of categories. The limited amount of hand-drawn sketch training data is leveraged by exploiting readily available image-level-annotated datasets of natural images containing a large number of classes. To bridge the domain gap, the classifier is trained on a sketch-like proxy domain derived from edges detected on natural images. We show that sketch recognition significantly benefits when the classifier is trained on sketch-like structures extracted from the co-segmented area rather than from the full image. Code: https://github.com/nikosips/CBNC . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13582 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification Ypsilantis, Nikolaos-Antonios Chum, Ondřej Computer Vision and Pattern Recognition This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are exploited: ImageNet classification-trained ViT, whose features are used to estimate rough object localization through intra-class token relevance, and a self-supervised DINO-ViT for intra-image token relevance. On recent challenging benchmarks, the method achieves state-of-the-art performance among methods trained with the same level of supervision (image labels) while being competitive with methods trained with pixel-level supervision (binary masks). The benefits of the proposed co-segmentation method are further demonstrated in the task of large-scale sketch recognition, that is, the classification of sketches into a wide range of categories. The limited amount of hand-drawn sketch training data is leveraged by exploiting readily available image-level-annotated datasets of natural images containing a large number of classes. To bridge the domain gap, the classifier is trained on a sketch-like proxy domain derived from edges detected on natural images. We show that sketch recognition significantly benefits when the classifier is trained on sketch-like structures extracted from the co-segmented area rather than from the full image. Code: https://github.com/nikosips/CBNC . |
| title | Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.13582 |