Dynamic Clustering Network for Unsupervised Semantic Segmentation

10/12/2022
by   Kehan Li, et al.
0

Recently, the ability of self-supervised Vision Transformer (ViT) to represent pixel-level semantic relationships promotes the development of unsupervised dense prediction tasks. In this work, we investigate transferring self-supervised ViT to unsupervised semantic segmentation task. According to the analysis that the pixel-level representations of self-supervised ViT within a single image achieve good intra-class compactness and inter-class discrimination, we propose the Dynamic Clustering Network (DCN) to dynamically infer the underlying cluster centers for different images. By training with the proposed modularity loss, the DCN learns to project a set of prototypes to cluster centers for pixel representations in each image and assign pixels to different clusters, resulting on dividing each image to class-agnostic regions. For achieving unsupervised semantic segmentation task, we treat it as a region classification problem. Based on the regions produced by the DCN, we explore different ways to extract region-level representations and classify them in an unsupervised manner. We demonstrate the effectiveness of the proposed method trough experiments on unsupervised semantic segmentation, and achieve state-of-the-art performance on PASCAL VOC 2012 unsupervised semantic segmentation task.

READ FULL TEXT

page 1

page 2

page 4

page 6

research
07/11/2022

Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations

In this paper, we show that recent advances in self-supervised feature l...
research
04/03/2023

Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation

In this work, we investigate performing semantic segmentation solely thr...
research
06/11/2021

KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation

In semantic segmentation, we aim to train a pixel-level classifier to as...
research
03/16/2022

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Unsupervised semantic segmentation aims to discover and localize semanti...
research
12/06/2019

Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning

Mobile robots operating in unknown urban environments encounter a wide r...
research
02/11/2021

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

Being able to learn dense semantic representations of images without sup...
research
04/14/2023

Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation

Self-supervised pre-training strategies have recently shown impressive r...

Please sign up or login with your details

Forgot password? Click here to reset