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/mcg-nju/deqdet

공식 코드

Deep Equilibrium Object Detection

https://github.com/mcg-nju/link

공식 코드

LinK: Linear Kernel for LiDAR-based 3D Perception

https://github.com/mcg-nju/logn

공식 코드

Logit Normalization for Long-tail Object Detection

https://github.com/mcg-nju/sparsebev

공식 코드

SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

https://github.com/mcg-nju/stageinteractor

공식 코드

StageInteractor: Query-based Object Detector with Cross-stage Interaction

https://github.com/mcg-nju/structured-sparse-rcnn

공식 코드

Structured Sparse R-CNN for Direct Scene Graph Generation

https://github.com/mcg-nju/tia

공식 코드

Task-specific Inconsistency Alignment for Domain Adaptive Object Detection

https://github.com/mcv-m6-video/mcv-m6-2021-team4

공식 코드

Video Surveillance for Road Traffic Monitoring

https://github.com/mczhuge/ICON

공식 코드

Salient Object Detection via Integrity Learning

https://github.com/mecarill/2pcnet

공식 코드

2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection

https://github.com/mediabrain-sjtu/where2comm

공식 코드

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

https://github.com/megvii-basedetection/bevdepth

공식 코드

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

https://github.com/megvii-basedetection/bevstereo

공식 코드

BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo

https://github.com/megvii-basedetection/denseteacher

공식 코드

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

https://github.com/megvii-model/CrowdDetection

공식 코드

Detection in Crowded Scenes: One Proposal, Multiple Predictions

https://github.com/megvii-model/DetNAS

공식 코드

DetNAS: Backbone Search for Object Detection

https://github.com/megvii-model/LabelEnc

공식 코드

LabelEnc: A New Intermediate Supervision Method for Object Detection

https://github.com/megvii-model/MOTR

공식 코드

MOTR: End-to-End Multiple-Object Tracking with Transformer

https://github.com/megvii-model/YOLOF

공식 코드

You Only Look One-level Feature

https://github.com/megvii-model/anchordetr

공식 코드

Anchor DETR: Query Design for Transformer-Based Object Detection

https://github.com/megvii-model/iter-e2edet

공식 코드

Progressive End-to-End Object Detection in Crowded Scenes

https://github.com/megvii-research/AnchorDETR

공식 코드

Anchor DETR: Query Design for Transformer-Based Object Detection

https://github.com/megvii-research/ICD

공식 코드

Instance-Conditional Knowledge Distillation for Object Detection

https://github.com/megvii-research/LGD

공식 코드

LGD: Label-guided Self-distillation for Object Detection

https://github.com/megvii-research/SOLQ

공식 코드

SOLQ: Segmenting Objects by Learning Queries

https://github.com/megvii-research/co-mining

공식 코드

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

https://github.com/megvii-research/cvpr2023-unidistill

공식 코드

UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View

https://github.com/megvii-research/far3d

공식 코드

Far3D: Expanding the Horizon for Surround-view 3D Object Detection

https://github.com/megvii-research/mdistiller

공식 코드

Decoupled Knowledge Distillation

https://github.com/megvii-research/motr

공식 코드

MOTR: End-to-End Multiple-Object Tracking with Transformer

https://github.com/megvii-research/petr

공식 코드

PETR: Position Embedding Transformation for Multi-View 3D Object Detection

https://github.com/megvii-research/revcol

공식 코드

Reversible Column Networks

https://github.com/megvii-research/us3l-cvpr2023

공식 코드

Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning

https://github.com/meharkhurana03/cm3d

공식 코드

Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection

https://github.com/meijieru/fast_advprop

공식 코드

Fast AdvProp

https://github.com/meituan-automl/visionllama

공식 코드

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

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