Papers with Code 아카이브

2D Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

15

평가표

20

보존된 평가 기록

57

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Mind23-2/MindCode-5/tree/main/pointtransformer

Point Transformer

https://github.com/Mind23-2/MindCode-5/tree/main/rcnn

RCNN-SliceNet: A Slice and Cluster Approach for Nuclei Centroid Detection in Three-Dimensional Fluorescence Microscopy Images

https://github.com/Mind23-2/MindCode-51

HarDNet: A Low Memory Traffic Network

https://github.com/Mind23-2/MindCode-52

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

https://github.com/Mind23-2/MindCode-53

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

https://github.com/Mind23-2/MindCode-58

Searching for MobileNetV3

https://github.com/Mind23-2/MindCode-63

Pyramid Scene Parsing Network

https://github.com/Mind23-2/MindCode-67

Deep Residual Learning for Image Recognition

https://github.com/Mind23-2/MindCode-70

Deep Residual Learning for Image Recognition

https://github.com/Mind23-2/MindCode-72

Squeeze-and-Excitation Networks

https://github.com/Mind23-2/MindCode-75

Fully-Convolutional Siamese Networks for Object Tracking

https://github.com/Mind23-2/MindCode-82

SSD: Single Shot MultiBox Detector

https://github.com/Mind23-2/MindCode-88/tree/main/SPPNet

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

https://github.com/Mind23-2/MindCode-93

Efficient Teacher: Semi-Supervised Object Detection for YOLOv5

https://github.com/MindCode-4/code-1/tree/main/van

Visual Attention Network

https://github.com/MindCode-4/code-1/tree/main/vit

Exploring Plain Vision Transformer Backbones for Object Detection

https://github.com/MindCode-4/code-10/tree/main/CME

Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection

https://github.com/MindCode-4/code-11/tree/main/corss-dataset-training

Cross-dataset Training for Class Increasing Object Detection

https://github.com/MindCode-4/code-11/tree/main/dropblock-a-regularization-method

DropBlock: A regularization method for convolutional networks

https://github.com/MindCode-4/code-12/tree/main/group-normalization

Group Normalization

https://github.com/MindCode-4/code-12/tree/main/lcn-master-ms

LCNN: Low-level Feature Embedded CNN for Salient Object Detection

https://github.com/MindCode-4/code-13/tree/main/ssFPN

ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection

https://github.com/MindCode-4/code-14/tree/main/AVA_hpa

RandAugment: Practical automated data augmentation with a reduced search space

https://github.com/MindCode-4/code-2/tree/main/owlvit

Scaling Open-Vocabulary Object Detection

https://github.com/MindCode-4/code-2/tree/main/poolformer

MetaFormer Is Actually What You Need for Vision

https://github.com/MindCode-4/code-3/tree/main/convnext

A ConvNet for the 2020s

https://github.com/MindCode-4/code-3/tree/main/convnextv2

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

https://github.com/MindCode-4/code-3/tree/main/deformable_detr

Deformable ConvNets v2: More Deformable, Better Results

https://github.com/MindCode-4/code-3/tree/main/detr

DETRs with Collaborative Hybrid Assignments Training

https://github.com/MindCode-4/code-3/tree/main/efficientnet

EfficientDet: Scalable and Efficient Object Detection

https://github.com/MindCode-4/code-3/tree/main/florence2

Florence: A New Foundation Model for Computer Vision

https://github.com/MindCode-4/code-3/tree/main/focalnet

Focal Modulation Networks

https://github.com/MindCode-4/code-4/tree/main/poolformer

MetaFormer Is Actually What You Need for Vision

https://github.com/MindCode-4/code-4/tree/main/rembert

Deep Residual Learning for Image Recognition

https://github.com/MindCode-4/code-5/tree/main/swin

Swin Transformer V2: Scaling Up Capacity and Resolution

https://github.com/MindCode-4/code-5/tree/main/table_transformer

TableFormer: Table Structure Understanding with Transformers

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