Papers with Code · CC BY-SA 4.0

CityPersons

아카이브 평가 22건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
DIW Loss	Reasonable MR^-2 6.23 Heavy MR^-2 28.37 Small MR^-2 7.36	Increasing pedestrian detection performance through weighting of detection impairing factors 2022-12-08	연결 없음
LSFM (Additional Data)	Reasonable MR^-2 6.38 Heavy MR^-2 24.73 Small MR^-2 7.90 Test Time 0.18	Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving 2023-01-01	연결 없음
Pedestron	Reasonable MR^-2 7.5 Heavy MR^-2 33.9 Partial MR^-2 5.7 Bare MR^-2 6.2 Small MR^-2 8.0 Medium MR^-2 3.0 Large MR^-2 4.3	Generalizable Pedestrian Detection: The Elephant In The Room 2020-03-19	코드 1
F2DNet (extra data)	Reasonable MR^-2 7.8 Heavy MR^-2 26.23 Small MR^-2 9.43 Test Time 0.44s/img	F2DNet: Fast Focal Detection Network for Pedestrian Detection 2022-03-04	코드 1 · 코드 2
LSFM	Reasonable MR^-2 8.5 Heavy MR^-2 31.9 Small MR^-2 8.8 Test Time 0.18	Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving 2023-01-01	연결 없음
F2DNet	Reasonable MR^-2 8.7 Heavy MR^-2 32.6 Small MR^-2 11.3 Test Time 0.44s/img	F2DNet: Fast Focal Detection Network for Pedestrian Detection 2022-03-04	코드 1 · 코드 2
ACSP	Reasonable MR^-2 9.3 Heavy MR^-2 46.3 Partial MR^-2 8.7 Bare MR^-2 5.6	Adapted Center and Scale Prediction: More Stable and More Accurate 2020-02-20	코드 1
VLPD	Reasonable MR^-2 9.4 Heavy MR^-2 43.1 Partial MR^-2 8.8 Bare MR^-2 6.1 Small MR^-2 10.9	VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision 2023-04-06	코드 1
SOLIDER	Reasonable MR^-2 9.7 Heavy MR^-2 39.4	Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks 2023-03-30	코드 1 · 코드 2 · 코드 3 · 코드 4
NMS-Loss	Reasonable MR^-2 10.08	NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection 2021-06-04	코드 1
Beta R-CNN	Reasonable MR^-2 10.6 Heavy MR^-2 47.1 Partial MR^-2 10.3 Bare MR^-2 6.4	Beta R-CNN: Looking into Pedestrian Detection from Another Perspective 2022-10-23	연결 없음
FRCNN+FPN-Res50+refined feature map+Crowdhuman	Reasonable MR^-2 10.67	CrowdHuman: A Benchmark for Detecting Human in a Crowd 2018-04-30	코드 1
NOH-NMS	Reasonable MR^-2 10.8 Heavy MR^-2 53.0 Partial MR^-2 11.2 Bare MR^-2 6.6	NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination 2020-07-27	코드 1
CSP (with offset) + ResNet-50	Reasonable MR^-2 11.0 Heavy MR^-2 49.3 Partial MR^-2 10.4 Bare MR^-2 7.3 Small MR^-2 16.0 Medium MR^-2 3.7 Large MR^-2 6.5 Test Time 0.33s/img	Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection 2019-04-05	코드 1 · 코드 2
ALFNet	Reasonable MR^-2 12.0 Heavy MR^-2 51.9 Partial MR^-2 11.4 Bare MR^-2 8.4 Small MR^-2 19.0 Medium MR^-2 5.7 Large MR^-2 6.6 Test Time 0.27	Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting 2018-09-01	코드 1
OR-CNN	Reasonable MR^-2 12.8 Heavy MR^-2 55.7 Partial MR^-2 15.3 Bare MR^-2 6.7	Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd 2018-07-23	연결 없음
RepLoss	Reasonable MR^-2 13.2 Heavy MR^-2 56.9 Partial MR^-2 16.8 Bare MR^-2 7.6	Repulsion Loss: Detecting Pedestrians in a Crowd 2017-11-21	코드 1 · 코드 2
TLL+MRF	Reasonable MR^-2 14.4 Heavy MR^-2 52.0 Partial MR^-2 15.9 Bare MR^-2 9.2	Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation 2018-07-04	연결 없음
FRCNN+Seg	Reasonable MR^-2 14.8 Small MR^-2 22.6 Medium MR^-2 6.7 Large MR^-2 8.0	CityPersons: A Diverse Dataset for Pedestrian Detection 2017-02-19	코드 1 · 코드 2
FRCNN	Reasonable MR^-2 15.4 Small MR^-2 25.6 Medium MR^-2 7.2 Large MR^-2 7.9	CityPersons: A Diverse Dataset for Pedestrian Detection 2017-02-19	코드 1 · 코드 2
TLL	Reasonable MR^-2 15.5 Heavy MR^-2 53.6 Partial MR^-2 17.2 Bare MR^-2 10.0	Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation 2018-07-04	연결 없음
ACSP + EuroCity Persons	Heavy MR^-2 42.5 Partial MR^-2 6.9 Bare MR^-2 4.9	Adapted Center and Scale Prediction: More Stable and More Accurate 2020-02-20	코드 1