Crowd Counting On Shanghaitech A

Metrics

MAE

Results

Performance results of various models on this benchmark

		Paper Title
Zhang et al.	181.8	Cross-Scene Crowd Counting via Deep Convolutional Neural Networks
MCNN	110.2	Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Cascaded-MTL	101.3	CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Switch-CNN	90.4	Switching Convolutional Neural Network for Crowd Counting
ACSCP	75.7	Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
SAFECount	73.70	Few-shot Object Counting with Similarity-Aware Feature Enhancement
CP-CNN	73.6	Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs
Liu et al.	73.6	Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
D-ConvNet	73.5	Crowd Counting With Deep Negative Correlation Learning
IG-CNN	72.5	Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN
ic-CNN	68.5	Iterative Crowd Counting
CSRNet	68.2	CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
SANet	67.0	Scale Aggregation Network for Accurate and Efficient Crowd Counting
LSC-CNN	66.4	Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
CSRNet-EBC	66.3	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
OrdinalEntropy	65.6	Improving Deep Regression with Ordinal Entropy
CAN	62.3	Context-Aware Crowd Counting
DMCount-EBC	62.3	CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
FusionCount	62.2	FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion
DM-Count	59.7	Distribution Matching for Crowd Counting

0 of 34 row(s) selected.

Command Palette

Crowd Counting On Shanghaitech A

Metrics

Results