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/weiwang31/icemamba
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/wenquanlu/handrefiner
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
https://github.com/wentao99/pix2pixHD
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
https://github.com/whatseven/UrbanScene3D
Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset
https://github.com/windwithforce/lane-detection
Towards End-to-End Lane Detection: an Instance Segmentation Approach
https://github.com/wolny/pytorch-3dunet
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
https://github.com/wongkinyiu/yolov9
https://github.com/wsjzha/deep-high-resolution-net.pytorch
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/wslerry/yolov5
https://github.com/wsx66848/detection
https://github.com/wsx66848/tsd
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
https://github.com/wusize/harmon
https://github.com/wvangansbeke/Unsupervised-Classification
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
https://github.com/xggIoU/GCNet_global_context_module_tensorflow
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
https://github.com/xiaohu2015/pvt_detectron2
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
https://github.com/xiaohu2015/swint_detectron2
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/xiuyu0000/new_papers_codes/tree/main/Pix2PixHD
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
https://github.com/xiuyu0000/papers_with_examples/tree/main/maskrcnn
https://github.com/xjnpark/ds
https://github.com/xmu-xiaoma666/External-Attention-pytorch
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
https://github.com/xmu-xiaoma666/External-Attention-pytorch/blob/master/attention/HaloAttention.py
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
https://github.com/xunhen/py-faster-rcnn-wjc
https://github.com/xurige1995/3shnet
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
https://github.com/xushilin1/fashionformer
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
https://github.com/xuxw98/esam
https://github.com/xy-guo/mmdetection_kitti
https://github.com/xzabg/faster-rcnn-with-Caltech
https://github.com/yan-roo/SpineNet-Pytorch
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
https://github.com/yangyangxu0/demt
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/yangyucheng000/HRNetW48_cls
Deep High-Resolution Representation Learning for Visual Recognition
https://github.com/yangyucheng000/MSpaper/tree/main/Unet3d
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
https://github.com/yangyucheng000/Mask-RCNN
https://github.com/yangyucheng000/University/tree/main/model-1/oneformer
OneFormer: One Transformer to Rule Universal Image Segmentation
https://github.com/yangyucheng000/University/tree/main/model-3/swin
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/yangyucheng000/maskrcnn_mobilenetv1
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.