Papers with Code 아카이브

Instance Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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-ai/models/tree/master/research/cv/res2net

Res2Net: A New Multi-scale Backbone Architecture

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/CoTAttention.py

Contextual Transformer Networks for Visual Recognition

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/CrissCrossAttention.py

CCNet: Criss-Cross Attention for Semantic Segmentation

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/Crossformer.py

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/ECAAttention.py

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/EPSA.py

EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/ExternalAttention.py

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/ShuffleAttention.py

SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/TripletAttention.py

Rotate to Attend: Convolutional Triplet Attention Module

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/CoaT.py

Co-Scale Conv-Attentional Image Transformers

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/HATNet.py

Vision Transformers with Hierarchical Attention

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/swin_transformer.py

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/swin_transformer_v2.py

Swin Transformer V2: Scaling Up Capacity and Resolution

https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/res2net.py

Res2Net: A New Multi-scale Backbone Architecture

https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/rexnet.py

Rethinking Channel Dimensions for Efficient Model Design

https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/swin_transformer.py

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://github.com/mindspore-lab/mindone

Deep High-Resolution Representation Learning for Human Pose Estimation

https://github.com/minerva-ml/open-solution-mapping-challenge

TernausNetV2: Fully Convolutional Network for Instance Segmentation

https://github.com/minghanz/LaneNet

Towards End-to-End Lane Detection: an Instance Segmentation Approach

https://github.com/mingyuliutw/UNIT

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

https://github.com/minimaxir/person-blocker

Microsoft COCO: Common Objects in Context

https://github.com/minoot7/Lane-Detection-Transfer-Learning

Key Points Estimation and Point Instance Segmentation Approach for Lane Detection

https://github.com/miquel-espinosa/samantics

No time to train! Training-Free Reference-Based Instance Segmentation

https://github.com/mirthai/csa-net

Non-local Neural Networks

https://github.com/mirzaevinom/data_science_bowl_2018

https://github.com/mistasse/modulom-panopticdeeplab

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

https://github.com/mit-han-lab/sparsevit

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

https://github.com/mks0601/PoseFix_RELEASE

Deep High-Resolution Representation Learning for Human Pose Estimation

https://github.com/mlf-core/liver-ct-segmentation

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

https://github.com/mlpc-ucsd/PRTR

Deep High-Resolution Representation Learning for Visual Recognition

https://github.com/mnikitin/ECANet

Gated Channel Transformation for Visual Recognition

https://github.com/mnikitin/EvoNorm

Evolving Normalization-Activation Layers

https://github.com/mnikitin/channel-attention

Gated Channel Transformation for Visual Recognition

https://github.com/moabarar/nemar

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

https://github.com/mohitktanwr/Deep-Stem-ResNeSt-ISPRS

ResNeSt: Split-Attention Networks

https://github.com/mohitktanwr/ResNeSt_Inverse

ResNeSt: Split-Attention Networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.