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/VRI-UFPR/IDA

공식 코드

IDA: Improved Data Augmentation Applied to Salient Object Detection

https://github.com/Vegeta2020/CIA-SSD

공식 코드

CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

https://github.com/Vegeta2020/SE-SSD

공식 코드

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

https://github.com/VerwimpEli/CLAD

공식 코드

CLAD: A realistic Continual Learning benchmark for Autonomous Driving

https://github.com/VimsLab/SODAWideNet

공식 코드

SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training

https://github.com/VisDrone/DroneCrowd

공식 코드

Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark

https://github.com/VisDrone/VisDrone-Dataset

공식 코드

Detection and Tracking Meet Drones Challenge

https://github.com/Visual-Attention-Network/VAN-Classification

공식 코드

Visual Attention Network

https://github.com/VisualAIKHU/SAMPD

공식 코드

Multispectral Pedestrian Detection with Sparsely Annotated Label

https://github.com/Vladimir2506/Pointformer

공식 코드

3D Object Detection with Pointformer

https://github.com/WHUHLX/CATS

공식 코드

Unmixing Convolutional Features for Crisp Edge Detection

https://github.com/WISION-Lab/event-nn-pytorch

공식 코드

Event Neural Networks

https://github.com/WISION-Lab/event-nn-tf

공식 코드

Event Neural Networks

https://github.com/WISION-Lab/eventful-transformer

공식 코드

Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers

https://github.com/WXinlong/ForeSeE

공식 코드

Task-Aware Monocular Depth Estimation for 3D Object Detection

https://github.com/WXinlong/SOLO

공식 코드

SOLOv2: Dynamic and Fast Instance Segmentation

https://github.com/WYFDUT/MonoASRH

공식 코드

Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection

https://github.com/WanXiaopei/aadi

공식 코드

Augmenting Anchors by the Detector Itself

https://github.com/WangLibo1995/GeoSeg

공식 코드

UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery

https://github.com/WangYueFt/pillar-od

공식 코드

Pillar-based Object Detection for Autonomous Driving

https://github.com/Wangjing1551/LogoDet-3K-Dataset

공식 코드

LogoDet-3K: A Large-Scale Image Dataset for Logo Detection

https://github.com/WangyiNTU/Point-supervised-crowd-detection

공식 코드

A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds

https://github.com/WaterScenes/USVTrack-Baseline-YOLO-Tracking

공식 코드

WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces

https://github.com/WeiZongqi/CG-Net

공식 코드

Learning Calibrated-Guidance for Object Detection in Aerial Images

https://github.com/WeijingShi/Point-GNN

공식 코드

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

https://github.com/WenqiangX/ese_seg

공식 코드

Explicit Shape Encoding for Real-Time Instance Segmentation

https://github.com/Westlake-AI/A2MIM

공식 코드

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

https://github.com/Westlake-AI/MogaNet

공식 코드

MogaNet: Multi-order Gated Aggregation Network

https://github.com/Westlake-AI/openmixup

공식 코드

Exploring Localization for Self-supervised Fine-grained Contrastive Learning

https://github.com/WinFrand/MELM

공식 코드

Min-Entropy Latent Model for Weakly Supervised Object Detection

https://github.com/Windere/snn-cvt-dual-phase

공식 코드

Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization

https://github.com/Winfrand/C-MIL

공식 코드

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

https://github.com/WongKinYiu/CrossStagePartialNetworks

공식 코드

CSPNet: A New Backbone that can Enhance Learning Capability of CNN

https://github.com/WongKinYiu/ScaledYOLOv4

공식 코드

Scaled-YOLOv4: Scaling Cross Stage Partial Network

https://github.com/WongKinYiu/YOLO

공식 코드

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

https://github.com/WongKinYiu/yolor

공식 코드

You Only Learn One Representation: Unified Network for Multiple Tasks

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