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/huangyebiaoke/steel-pipe-weld-defect-detection

공식 코드

Deep Learning Based Steel Pipe Weld Defect Detection

https://github.com/huangyh98/advreal

공식 코드

AdvReal: Adversarial Patch Generation Framework with Application to Adversarial Safety Evaluation of Object Detection Systems

https://github.com/huangzhe885/codiff

공식 코드

CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection

https://github.com/huangzhe885/roco

공식 코드

RoCo:Robust Collaborative Perception By Iterative Object Matching and Pose Adjustment

https://github.com/huangzizheng01/shufflemamba

공식 코드

Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training

https://github.com/huanranchen/AdversarialAttacks

공식 코드

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

https://github.com/huawei-noah/CV-backbones

공식 코드

An Image Patch is a Wave: Phase-Aware Vision MLP

https://github.com/huawei-noah/Efficient-Computing

공식 코드

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection/Gold-YOLO

공식 코드

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

https://github.com/huawei-noah/efficient-ai-backbones

공식 코드

Vision GNN: An Image is Worth Graph of Nodes

https://github.com/huawei-noah/noah-research/tree/master/TokenFusion

공식 코드

Multimodal Token Fusion for Vision Transformers

https://github.com/huawei-noah/vega

공식 코드

An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization

https://github.com/hucaofighting/frn

공식 코드

Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection

https://github.com/huggingface/pytorch-image-models

공식 코드

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

https://github.com/huiminshii/dpnet

공식 코드

DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention

https://github.com/hujie-frank/SENet

공식 코드

Squeeze-and-Excitation Networks

https://github.com/hujiecpp/ISTR

공식 코드

ISTR: End-to-End Instance Segmentation with Transformers

https://github.com/hukenovs/hagrid

공식 코드

HaGRID - HAnd Gesture Recognition Image Dataset

https://github.com/human-analysis/MUXConv

공식 코드

MUXConv: Information Multiplexing in Convolutional Neural Networks

https://github.com/humza909/survery-image-mixing-and-deleting-for-data-augmentation

공식 코드

Survey: Image Mixing and Deleting for Data Augmentation

https://github.com/hungntt/LangXAI

공식 코드

LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks

https://github.com/hunterj-lin/activeteacher

공식 코드

Active Teacher for Semi-Supervised Object Detection

https://github.com/hunto/diffkd

공식 코드

Knowledge Diffusion for Distillation

https://github.com/hunto/dist_kd

공식 코드

Knowledge Distillation from A Stronger Teacher

https://github.com/hunto/lightvit

공식 코드

LightViT: Towards Light-Weight Convolution-Free Vision Transformers

https://github.com/hunto/maskd

공식 코드

Masked Distillation with Receptive Tokens

https://github.com/hust-jy/dds3d

공식 코드

DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection

https://github.com/hustgetlijun/RCAN

공식 코드

Carton dataset synthesis method for domain shift based on foreground texture decoupling and replacement

https://github.com/hustvl/LSFA

공식 코드

Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

https://github.com/hustvl/MSG-Transformer

공식 코드

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens

https://github.com/hustvl/QueryInst

공식 코드

Instances as Queries

https://github.com/hustvl/YOLOS

공식 코드

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

https://github.com/hustvl/azinorm

공식 코드

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception

https://github.com/hustvl/featurized-queryrcnn

공식 코드

Featurized Query R-CNN

https://github.com/hustvl/mim4d

공식 코드

MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning

https://github.com/hustvl/mimdet

공식 코드

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

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