Papers with Code 아카이브
Instance Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 36
- 보존된 평가 기록
- 338
Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/chufengt/ViRReq
공식 코드https://github.com/chunminghe/awesome-concealed-object-segmentation
공식 코드https://github.com/chwilms/sos
공식 코드SOS: Segment Object System for Open-World Instance Segmentation With Object Priors
https://github.com/chwilms/superpixelRefinement
공식 코드https://github.com/circleradon/apro
공식 코드https://github.com/clovaai/BESTIE
공식 코드https://github.com/clovaai/ECLIPSE
공식 코드ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
https://github.com/clovaai/pointwssis
공식 코드https://github.com/clovaai/rexnet
공식 코드https://github.com/clusterformer/clusterformer
공식 코드https://github.com/cmsflash/efficient-attention
공식 코드https://github.com/cocodataset/panopticapi
공식 코드https://github.com/code-iai/noctis
공식 코드NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
https://github.com/cogsys-tuebingen/FourierNet
공식 코드https://github.com/computational-cell-analytics/patho-sam
공식 코드https://github.com/congvvc/HyperSeg
공식 코드HyperSeg: Towards Universal Visual Segmentation with Large Language Model
https://github.com/constantinpape/cluster_tools
공식 코드Leveraging Domain Knowledge to Improve Microscopy Image Segmentation with Lifted Multicuts
https://github.com/constantinpape/torch-em
공식 코드https://github.com/cosim-lab/yolov8-to
공식 코드https://github.com/cosmoiknoslab/nulite
공식 코드NuLite -- Lightweight and Fast Model for Nuclei Instance Segmentation and Classification
https://github.com/cp3wan/dformer
공식 코드DFormer: Diffusion-guided Transformer for Universal Image Segmentation
https://github.com/cplab/annolid
공식 코드https://github.com/csccsccsccsc/brpnet
공식 코드Boundary-assisted Region Proposal Networks for Nucleus Segmentation
https://github.com/csdllab/mca
공식 코드https://github.com/ctu-vras/let-it-flow
공식 코드Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
https://github.com/cvlab-columbia/equi4rob
공식 코드https://github.com/cvlab-stonybrook/plm_ssl
공식 코드Precise Location Matching Improves Dense Contrastive Learning in Digital Pathology
https://github.com/cvmi-lab/pla
공식 코드https://github.com/czczup/vit-adapter
공식 코드https://github.com/czhang0528/MosaicOS
공식 코드MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
https://github.com/daijifeng001/TA-FCN
공식 코드https://github.com/damo-cv/elsa
공식 코드https://github.com/danganea/iMTFA
공식 코드https://github.com/danielshkao/thinkvideo
공식 코드ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts
https://github.com/davyneven/SpatialEmbeddings
공식 코드Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.