Papers with Code 아카이브
Image Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 13
- 보존된 평가 기록
- 34
Image Segmentation is a computer vision task that involves dividing an image into multiple segments or regions, each of which corresponds to a different object or part of an object. The goal of image segmentation is to assign a unique label or category to each pixel in the image, so that pixels with similar attributes are grouped together.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/cscyqj/miccai23-protocontra-sfda
공식 코드https://github.com/csyfjiang/mlla-unet
공식 코드MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentation
https://github.com/cuhk-aim-group/diffrect
공식 코드DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentation
https://github.com/curli-quan/slide-sam
공식 코드https://github.com/cuthbert-huang/cc-net
공식 코드Complementary consistency semi-supervised learning for 3D left atrial image segmentation
https://github.com/cuthbert-huang/cpcanet
공식 코드Channel prior convolutional attention for medical image segmentation
https://github.com/cvlab-stonybrook/tokensparse-for-medseg
공식 코드https://github.com/cwlee00/mfp
공식 코드MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
https://github.com/cxh-research/smaformer
공식 코드SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation
https://github.com/cy-xu/cosmic-conn
공식 코드Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel Images
https://github.com/cyb08/mambaclinix-pytorch
공식 코드https://github.com/cybonic/misagriculture
공식 코드Multispectral Image Segmentation in Agriculture: A Comprehensive Study on Fusion Approaches
https://github.com/cybus123456/hich-it-datasets
공식 코드https://github.com/cyh4/FCTSFN
공식 코드A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation
https://github.com/cys1102/fba-net
공식 코드https://github.com/cyt1202/byocl
공식 코드BYOCL: Build Your Own Consistent Latent with Hierarchical Representative Latent Clustering
https://github.com/dafne-imaging/dafne
공식 코드https://github.com/dair-iitd/c2fi4cv
공식 코드https://github.com/dair-iitd/guided-prompting-sam
공식 코드Guided Prompting in SAM for Weakly Supervised Cell Segmentation in Histopathological Images
https://github.com/dalifreire/tumor_regions_segmentation
공식 코드Hematoxylin and eosin stained oral squamous cell carcinoma histological images dataset
https://github.com/danganea/iMTFA
공식 코드https://github.com/danhntd/FS-CDIS
공식 코드The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
https://github.com/danielshkao/thinkvideo
공식 코드ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts
https://github.com/daniyanaj/dwinformer
공식 코드Medical Image Segmentation Using Directional Window Attention
https://github.com/danjacobellis/mpq
공식 코드https://github.com/davecasp/flowssm
공식 코드Landmark-free Statistical Shape Modeling via Neural Flow Deformations
https://github.com/david-stojanovski/echo_from_noise
공식 코드https://github.com/davidvandijcke/fdd
공식 코드Free Discontinuity Regression: With an Application to the Economic Effects of Internet Shutdowns
https://github.com/davidvandijcke/fdr
공식 코드Free Discontinuity Regression: With an Application to the Economic Effects of Internet Shutdowns
https://github.com/ddrrnn123/omni-seg
공식 코드https://github.com/deel-ai-papers/consema
공식 코드Conformal Prediction for Image Segmentation Using Morphological Prediction Sets
https://github.com/deep-unlearn/ISPRS-Classification-With-an-Edge
공식 코드Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection
https://github.com/deepmed-lab-ecnu/bcp
공식 코드Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
https://github.com/deepmed-lab-ecnu/fs_medsam2
공식 코드RevSAM2: Prompt SAM2 for Medical Image Segmentation via Reverse-Propagation without Fine-tuning
https://github.com/deepmed-lab-ecnu/magicnet
공식 코드MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.