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/MindSpore-scientific/code-10/tree/main/PolyLoss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
https://github.com/MindSpore-scientific/code-11/tree/main/PolyLoss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
https://github.com/MindSpore-scientific/code-11/tree/main/Uncertainty_Calibration_Object_Detection
Uncertainty Calibration and its Application to Object Detection
https://github.com/MindSpore-scientific/code-12/tree/main/EPRNet
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network
https://github.com/MindSpore-scientific/code-13/tree/main/PolyLoss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
https://github.com/MindSpore-scientific/code-14/tree/main/WaveCRN-master
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
https://github.com/MindSpore-scientific/code-14/tree/main/res_mlp_ms
https://github.com/MindSpore-scientific/code-2/tree/main/weakly-supervised
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
https://github.com/MindSpore-scientific/code-5/tree/main/polyloss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
https://github.com/MindSpore-scientific/code-6/tree/main/multi-task-learning-using-uncertainty-to
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
https://github.com/MindSpore-scientific/code-7/tree/main/ImageGPT
https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former
Masked-attention Mask Transformer for Universal Image Segmentation
https://github.com/MindSpore-scientific/code-8/tree/main/MicAugment
https://github.com/MindSpore-scientific/code-8/tree/main/PolyLoss
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
https://github.com/Mixture-of-Rookie/PASSL
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
https://github.com/MrGiovanni/Nested-UNet
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
https://github.com/Mrnoorsingh/car-parking
https://github.com/Mukosame/Zooming-Slow-Mo-CVPR-2020
https://github.com/Myyyr/transseg2d
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/NEUdeep/Swin-Transformer-Object-Detection
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/NMADALI97/PointCNN_Pytorch
https://github.com/NSCL/yolact_instance
https://github.com/NU-LL/lighttrack-
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/NVlabs/DiscoBox
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
https://github.com/NVlabs/PAMTRI
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/NVlabs/UnseenObjectClustering
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
https://github.com/NVlabs/contact_graspnet
https://github.com/NVlabs/industreallib
https://github.com/NZ99/bottleneck-transformer-flax
https://github.com/NaturalHistoryMuseum/semantic-segmentation
Semantic Instance Segmentation with a Discriminative Loss Function
https://github.com/NiravRaiyani/Mask-R-CNN-for-water-detection
https://github.com/OceanPang/Libra_R-CNN
https://github.com/Oichii/DeepPulse-pytorch
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
https://github.com/Okery/PyTorch-Simple-MaskRCNN
https://github.com/OpenFirework/pytorch_solov2
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.