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/chrisbahnsen/aau-rainsnow-eval
https://github.com/chrisbahnsen/rainremoval
https://github.com/chrisdxie/uois
Unseen Object Instance Segmentation for Robotic Environments
https://github.com/chuanqichen/deepcoaching
https://github.com/claud1234/clft
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
https://github.com/claud1234/fcn_transformer_object_segmentation
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
https://github.com/code-implementation1/Code1/tree/main/detr
https://github.com/code-implementation1/Code4/tree/main/IndexNet
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
https://github.com/code-implementation1/Code4/tree/main/hlg
Vision Transformers: From Semantic Segmentation to Dense Prediction
https://github.com/code-implementation1/Code6/tree/main/Non_local
https://github.com/code-implementation1/Code7/tree/main/ResNeXt
https://github.com/code-implementation1/Code7/tree/main/res2net
https://github.com/code-implementation1/Code7/tree/main/res2net_deeplabv3
https://github.com/code-implementation1/Code7/tree/main/resnext152_64x4d
https://github.com/code-implementation1/Code7/tree/main/retinanet_resnet101
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
https://github.com/code-implementation1/Code8/tree/main/SpineNet
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
https://github.com/code-implementation1/Code9/tree/main/MaskRCNN/maskrcnn_mobilenetv1
https://github.com/code-implementation1/Code9/tree/main/ShuffleNet
https://github.com/code-implementation1/Code9/tree/main/SwinTransformer
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/cokowpublic/Nuclei-Segmentation
https://github.com/coldsummerday/mmdetection-zhou
https://github.com/collectionslab/Omniscribe
https://github.com/collectionslab/annotations-computervision
https://github.com/collectionslab/book-annotation-classification
https://github.com/computational-cell-analytics/micro-sam
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
https://github.com/conceptofmind/Crossformer-flax
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
https://github.com/conradry/copy-paste-aug
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
https://github.com/craston/object_detection_cib
https://github.com/crowdai/crowdai-mapping-challenge-mask-rcnn
https://github.com/csiro-robotics/UPGen
Scalable learning for bridging the species gap in image-based plant phenotyping
https://github.com/csiro-robotics/UPGen-Webpage
https://github.com/csiro-robotics/UPGen_Webpage
https://github.com/csuzhuzhuxia/GlassDetect
https://github.com/cszzshi/SimD
RTMDet: An Empirical Study of Designing Real-Time Object Detectors
https://github.com/cuzyoung/crossearth
MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.