Crowd Counting On Shanghaitech B

Metrics

MAE

Results

Performance results of various models on this benchmark

		Paper Title
Zhang et al.	32.0	Cross-Scene Crowd Counting via Deep Convolutional Neural Networks
MCNN	26.4	Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Switch-CNN	21.6	Switching Convolutional Neural Network for Crowd Counting
CP-CNN	20.1	Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs
Cascaded-MTL	20	CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
D-ConvNet	18.7	Crowd Counting With Deep Negative Correlation Learning
ACSCP	17.2	Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
Liu et al.	13.7	Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
IG-CNN	13.6	Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN
ic-CNN	10.7	Iterative Crowd Counting
CSRNet	10.6	CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
SAFECount	9.98	Few-shot Object Counting with Similarity-Aware Feature Enhancement
OrdinalEntropy	9.1	Improving Deep Regression with Ordinal Entropy
APGCC	8.7	Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance
SANet	8.4	Scale Aggregation Network for Accurate and Efficient Crowd Counting
LSC-CNN	8.1	Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
CAN	7.8	Context-Aware Crowd Counting
DM-Count	7.4	Distribution Matching for Crowd Counting
DMCount-EBC	7.0	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
CSRNet-EBC	6.9	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification

0 of 31 row(s) selected.

Command Palette

Crowd Counting On Shanghaitech B

Metrics

Results