Papers with Code · CC BY-SA 4.0

ShanghaiTech B

아카이브 평가 32건 · 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
EBC-ZIP-B	MAE 5.51 RMSE 8.63	EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression 2025-06-24	코드 1
PSL-Net	MAE 5.8 RMSE 9.2	Crowd Counting and Individual Localization Using Pseudo Square Label 2024-05-13	연결 없음
CLIP-EBC (ViT-L/14)	MAE 5.9 RMSE 9.2	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 2024-03-14	코드 1
CLIP-EBC (ResNet50)	MAE 6.0 RMSE 10.1	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 2024-03-14	코드 1
GauNet (ResNet-50)	MAE 6.0	Rethinking Spatial Invariance of Convolutional Networks for Object Counting 2022-06-10	코드 1
SGANet	MAE 6.3	Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss 2019-11-18	코드 1
M-SFANet+M-SegNet	MAE 6.32 MSE 10.06	Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting 2020-03-12	코드 1 · 코드 2
SPANet	MAE 6.5	Learning Spatial Awareness to Improve Crowd Counting 2019-09-16	연결 없음
CLIP-EBC (ViT-B/16)	MAE 6.6 RMSE 10.5	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 2024-03-14	코드 1
SGANet + CL	MAE 6.6	Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss 2019-11-18	코드 1
S-DCNet	MAE 6.7	From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer 2019-08-15	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
FusionCount	MAE 6.9 MSE 11.8	FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion 2022-02-28	코드 1
CSRNet-EBC	MAE 6.9 RMSE 11.3	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 2024-03-14	코드 1
DMCount-EBC	MAE 7.0 RMSE 10.9	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification 2024-03-14	코드 1
DM-Count	MAE 7.4	Distribution Matching for Crowd Counting 2020-09-28	코드 1
CAN	MAE 7.8	Context-Aware Crowd Counting 2018-11-26	코드 1 · 코드 2 · 코드 3
LSC-CNN	MAE 8.1	Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection 2019-06-18	코드 1 · 코드 2
SANet	MAE 8.4	Scale Aggregation Network for Accurate and Efficient Crowd Counting 2018-09-01	코드 1
APGCC	MAE 8.7	Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance 2024-05-17	코드 1
OrdinalEntropy	MAE 9.1 MSE 14.5	Improving Deep Regression with Ordinal Entropy 2023-01-21	코드 1
SAFECount	MAE 9.98	Few-shot Object Counting with Similarity-Aware Feature Enhancement 2022-01-22	코드 1
CSRNet	MAE 10.6	CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes 2018-02-27	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
ic-CNN	MAE 10.7	Iterative Crowd Counting 2018-07-26	연결 없음
IG-CNN	MAE 13.6	Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN 2018-07-26	연결 없음
Liu et al.	MAE 13.7	Leveraging Unlabeled Data for Crowd Counting by Learning to Rank 2018-03-08	코드 1
ACSCP	MAE 17.2	Crowd Counting via Adversarial Cross-Scale Consistency Pursuit 2018-06-01	코드 1
D-ConvNet	MAE 18.7	Crowd Counting With Deep Negative Correlation Learning 2018-06-01	코드 1
Cascaded-MTL	MAE 20	CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting 2017-07-30	코드 1
CP-CNN	MAE 20.1	Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs 2017-08-02	연결 없음
Switch-CNN	MAE 21.6	Switching Convolutional Neural Network for Crowd Counting 2017-08-01	코드 1