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/kostas1515/gol
공식 코드Long-tailed Instance Segmentation using Gumbel Optimized Loss
https://github.com/kostas1515/iif
공식 코드https://github.com/koyeongmin/PINet
공식 코드Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
https://github.com/koyeongmin/PINet_new
공식 코드Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
https://github.com/kreshuklab/spoco
공식 코드Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings
https://github.com/kruzaeva/activity-cell-tracking
공식 코드Cell tracking for live-cell microscopy using an activity-prioritized assignment strategy
https://github.com/kulikovv/DeepColoring
공식 코드https://github.com/kulikovv/harmonic
공식 코드Instance Segmentation of Biological Images Using Harmonic Embeddings
https://github.com/kumuji/anomaly-benchmark-suite
공식 코드https://github.com/kumuji/ugains
공식 코드https://github.com/labdeeman7/cholec_instance_seg
공식 코드CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
https://github.com/lakmalnd/Vec2Instance
공식 코드Vec2Instance: Parameterization for Deep Instance Segmentation
https://github.com/laughtervv/SGPN
공식 코드SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
https://github.com/lavreniuk/evp
공식 코드https://github.com/ldknight/pm-vis-plus
공식 코드PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation
https://github.com/leaplabthu/dat
공식 코드DAT++: Spatially Dynamic Vision Transformer with Deformable Attention
https://github.com/leaplabthu/gsva
공식 코드GSVA: Generalized Segmentation via Multimodal Large Language Models
https://github.com/leaplabthu/lasnet
공식 코드https://github.com/lee-gihun/mediar
공식 코드MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
https://github.com/leiyi-hu/mona
공식 코드https://github.com/lely475/ocelot23algo
공식 코드SoftCTM: Cell detection by soft instance segmentation and consideration of cell-tissue interaction
https://github.com/leonnnop/locater
공식 코드Local-Global Context Aware Transformer for Language-Guided Video Segmentation
https://github.com/leoxiaobin/deep-high-resolution-net.pytorch
공식 코드Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/levan92/occlusion-copy-paste
공식 코드Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
https://github.com/lhaof/nuseg
공식 코드Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework
https://github.com/liamlian0727/uiis10k
공식 코드https://github.com/liamlian0727/underwatersam2eval
공식 코드Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment
https://github.com/liamlian0727/usis10k
공식 코드https://github.com/lichengunc/MAttNet
공식 코드MAttNet: Modular Attention Network for Referring Expression Comprehension
https://github.com/lifuguan/uplvp
공식 코드Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
https://github.com/lihaoliu-cambridge/simultaneous_semantic_and_instance_segmentation
공식 코드Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting
https://github.com/linfengyuan1997/losh
공식 코드LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
https://github.com/linwei-chen/lis
공식 코드https://github.com/linwei-chen/seg-aliasing
공식 코드https://github.com/liruilong940607/OCHumanApi
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.