SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 12 Jun 2024.
Builds on
19 of 29 references.
References · 19
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2023Segment Anythingcited by 8,234
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2020Exploring Simple Siamese Representation Learningcited by 2,866
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
- 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
- 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
- 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
7 more
- 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
- 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
- 2022Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learningcited by 115
- 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
- 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
- 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
- 2022ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentationcited by 42
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.