Scale Aggregation Network for Accurate and Efficient Crowd Counting

ECCV 2018  ·  Xinkun Cao, Zhipeng Wang, Yanyun Zhao, Fei Su ·

In this paper, we propose a novel encoder-decoder network, called extit{Scale Aggregation Network (SANet)}, for accurate and efficient crowd counting. The encoder extracts multi-scale features with scale aggregation modules and the decoder generates high-resolution density maps by using a set of transposed convolutions. Moreover, we find that most existing works use only Euclidean loss which assumes independence among each pixel but ignores the local correlation in density maps. Therefore, we propose a novel training loss, combining of Euclidean loss and local pattern consistency loss, which improves the performance of the model in our experiments. In addition, we use normalization layers to ease the training process and apply a patch-based test scheme to reduce the impact of statistic shift problem. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on four major crowd counting datasets and our method achieves superior performance to state-of-the-art methods while with much less parameters.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Crowd Counting UCF CC 50 SANet MAE 258.4 # 9

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Crowd Counting ShanghaiTech A SANet MAE 67.0 # 19
Crowd Counting ShanghaiTech B SANet MAE 8.4 # 15
Crowd Counting WorldExpo’10 SANet Average MAE 8.2 # 6

Methods


No methods listed for this paper. Add relevant methods here