Work

Simsam: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation

Year: 2024

Type: conference-paper

Abstract: 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.

Source: Proceedings - International Conference on Image Processing

DOI: 10.1109/icip51287.2024.10647970

Authors: Chanda Grover Kamra, Indra Deep Mastan, Nitin Kumar, Debayan Gupta

Institutions: Ashoka University, Indian Institute of Technology BHU, Shiv Nadar University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4402916551

FWCI: 0.842

Cites: 19

Cited by: 4

Related to: 10