Papers with Code 아카이브

Unsupervised Semantic Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 1
평가표: 18
보존된 평가 기록: 97

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

<span style="color:grey; opacity: 0.6">( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/m-arda-aydn/itaclip

공식 코드

ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements

https://github.com/mc-lan/proxyclip

공식 코드

ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

https://github.com/mc-lan/smooseg

공식 코드

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

https://github.com/merantix-momentum/stego-studies

공식 코드

Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation

https://github.com/mhamilton723/STEGO

공식 코드

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

https://github.com/mkuuwaujinga/leopart

공식 코드

Self-Supervised Learning of Object Parts for Semantic Segmentation

https://github.com/mlzxy/flowdino

공식 코드

Optical Flow boosts Unsupervised Localization and Segmentation

https://github.com/paulcouairon/diffcut

공식 코드

DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

https://github.com/robin-karlsson0/vice

공식 코드

ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment

https://github.com/ryersonmultimedialab/dynaseg

공식 코드

DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity

https://github.com/scut-bip-lab/pointdc

공식 코드

PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering

https://github.com/shjo-april/TTD

공식 코드

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

https://github.com/shjo-april/coin

공식 코드

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation

https://github.com/smsd75/timetuning

공식 코드

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

https://github.com/stegmuel/croc

공식 코드

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

https://github.com/tianxiang-hao/urban1960satseg

공식 코드

Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20$^{th}$ century Urban Landscapes with Satellite Imageries

https://github.com/twke18/hsg

공식 코드

Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers

https://github.com/u2seg/u2seg

공식 코드

Unsupervised Universal Image Segmentation

https://github.com/valeoai/found

공식 코드

Unsupervised Object Localization: Observing the Background to Discover Objects

https://github.com/visinf/cups

공식 코드

Scene-Centric Unsupervised Panoptic Segmentation

https://github.com/visinf/primaps

공식 코드

Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals

https://github.com/vlar-group/growsp

공식 코드

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

https://github.com/vlar-group/logosp

공식 코드

LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds

https://github.com/vobecant/DriveAndSegment

공식 코드

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation

https://github.com/wvangansbeke/MaskDistill

공식 코드

Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation

https://github.com/wvangansbeke/Unsupervised-Semantic-Segmentation

공식 코드

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

https://github.com/xmed-lab/mssg

공식 코드

Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic Grouping

https://github.com/xu-ji/IIC

공식 코드

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

https://github.com/yingqinghe/shadow-removal-via-generative-priors

공식 코드

Unsupervised Portrait Shadow Removal via Generative Priors

https://github.com/zadaianchuk/comus

공식 코드

Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations

https://github.com/zdk258/CorrCLIP

공식 코드

CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation

https://github.com/zwwwayne/densesiam

공식 코드

Dense Siamese Network for Dense Unsupervised Learning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.