Unsupervised Semantic Segmentation

65 papers with code • 18 benchmarks • 9 datasets

Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.

( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )

Most implemented papers

Deep Clustering for Unsupervised Learning of Visual Features

facebookresearch/deepcluster ECCV 2018

In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

xu-ji/IIC ICCV 2019

The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.

Large-scale Unsupervised Semantic Segmentation

LUSSeg/ImageNet-S 6 Jun 2021

In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

mhamilton723/STEGO ICLR 2022

Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation.

Mumford-Shah Loss Functional for Image Segmentation with Deep Learning

luoxd1996/wsl4mis 5 Apr 2019

This loss function is based on the observation that the softmax layer of deep neural networks has striking similarity to the characteristic function in the Mumford-Shah functional.

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

layumi/Seg-Uncertainty 8 Mar 2020

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

wvangansbeke/Unsupervised-Semantic-Segmentation ICCV 2021

To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings.

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering

janghyuncho/PiCIE CVPR 2021

With our novel learning objective, our framework can learn high-level semantic concepts.

ReCo: Retrieve and Co-segment for Zero-shot Transfer

NoelShin/reco 14 Jun 2022

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment.

What the DAAM: Interpreting Stable Diffusion Using Cross Attention

castorini/daam 10 Oct 2022

Large-scale diffusion neural networks represent a substantial milestone in text-to-image generation, but they remain poorly understood, lacking interpretability analyses.