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/tsing-cv/DetNet
https://github.com/ttppss/mmdetection
https://github.com/tuananh1007/Associatively-Segmenting-Instances-and-Semantics-in-Point-Clouds
Associatively Segmenting Instances and Semantics in Point Clouds
https://github.com/tuanzhangCS/res2net-on-mxnet
https://github.com/tui-nicr/nicr-scene-analysis-datasets
Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
https://github.com/tusimple/sst
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels
https://github.com/tweedlemoon/DSAC
https://github.com/ubc-vision/DwNet
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
https://github.com/ucas-vg/p2bnet
P2Object: Single Point Supervised Object Detection and Instance Segmentation
https://github.com/ucuapps/WSMIS
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
https://github.com/ultralytics/ultralytics
https://github.com/ultralytics/yolov5
https://github.com/universea/SOLOv2
https://github.com/urbaneman/mmdetection_mobilenet
https://github.com/ustc-imcl/hst-for-compressed-image-sr
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/v1viswan/Domain_adaptation_in_HRNet
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks
https://github.com/vasgaowei/TS-CAM
Conformer: Local Features Coupling Global Representations for Visual Recognition
https://github.com/vasgaowei/ts-cam-voc
Conformer: Local Features Coupling Global Representations for Visual Recognition
https://github.com/vikashchalla123/mmdet_b1.2.0_fork
https://github.com/vimalabs/VIMA
https://github.com/vincrichard/EfficientPS
https://github.com/visionNoob/hrnet_pytorch
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/visipedia/imat_comp
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
https://github.com/vitae-transformer/qformer
Exploring Plain Vision Transformer Backbones for Object Detection
https://github.com/vlcekl/n2n-tomo
https://github.com/voidrank/DiscoBox
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
https://github.com/voidrank/SCOT
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
https://github.com/vov-net/VoVNet-Detectron
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
https://github.com/vov-net/VoVNet-FCOS
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
https://github.com/w-sugar/mmdetection
https://github.com/w-sugar/prtr
Deep High-Resolution Representation Learning for Visual Recognition
https://github.com/waiyulam/ORCNN
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
https://github.com/wandb/awesome-dl-projects
https://github.com/wangermeng2021/PVT-tensorflow2
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.