SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913387657560064 |
|---|---|
| author | Kamra, Chanda Grover Mastan, Indra Deep Kumar, Nitin Gupta, Debayan |
| author_facet | Kamra, Chanda Grover Mastan, Indra Deep Kumar, Nitin Gupta, Debayan |
| contents | Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to compute the Semantic Affinity Matrix, which is significant for unsupervised image segmentation. Given an image, SIMSAM first extracts features using pre-trained DINO-ViT, then projects the features to predict the correlations of dense features in a non-contrastive way. We show applications of the Semantic Affinity Matrix in object segmentation and semantic segmentation tasks. Our code is available at https://github.com/chandagrover/SimSAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07986 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation Kamra, Chanda Grover Mastan, Indra Deep Kumar, Nitin Gupta, Debayan Computer Vision and Pattern Recognition Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to compute the Semantic Affinity Matrix, which is significant for unsupervised image segmentation. Given an image, SIMSAM first extracts features using pre-trained DINO-ViT, then projects the features to predict the correlations of dense features in a non-contrastive way. We show applications of the Semantic Affinity Matrix in object segmentation and semantic segmentation tasks. Our code is available at https://github.com/chandagrover/SimSAM. |
| title | SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.07986 |