Adaptive Depth Network for Crowd Counting And Beyond

Crowd counting is a challenging computer vision task which aims to estimate people count in crowded scenes. Although CNN-based methods have designed multi-scale or multicolumn structures to cope with scale variation within one image, the variety of distribution features among different images has not been taken into consideration, which is difficult to handle in a fixed scheme. In this paper, we propose a multi-output structure network named Adaptive Depth Network (ADNet) that can adaptively adjust the network’s depth according to the inputs’ features. This flexible model introduces extra output blocks into internal layers to exploit their representation abilities and selects the output from the output block that produces the best confidence value as the final result. In our experiments on three crowd counting datasets, ADNet shows a consistent improvement. Moreover, ablation study also proves the effectiveness of the multi-output structure on both crowd counting datasets and CIFAR-100.

[1]  Ling Shao,et al.  Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Haroon Idrees,et al.  Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds , 2018, ECCV.

[3]  Tudor Dumitras,et al.  Shallow-Deep Networks: Understanding and Mitigating Network Overthinking , 2018, ICML.

[4]  Yuhong Li,et al.  CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Pascal Fua,et al.  Context-Aware Crowd Counting , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Hiroshi Inoue.  Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level , 2019, AISTATS.

[8]  Li Pan,et al.  ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Shenghua Gao,et al.  Single-Image Crowd Counting via Multi-Column Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Shiv Surya,et al.  Switching Convolutional Neural Network for Crowd Counting , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Vishal M. Patel,et al.  Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  Ran El-Yaniv,et al.  SelectiveNet: A Deep Neural Network with an Integrated Reject Option , 2019, ICML.

[13]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[14]  Haroon Idrees,et al.  Multi-source Multi-scale Counting in Extremely Dense Crowd Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Larry S. Davis,et al.  BlockDrop: Dynamic Inference Paths in Residual Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Fei Su,et al.  Scale Aggregation Network for Accurate and Efficient Crowd Counting , 2018, ECCV.

[17]  Venkatesh Saligrama,et al.  Adaptive Neural Networks for Efficient Inference , 2017, ICML.

[18]  Qijun Chen,et al.  Revisiting Perspective Information for Efficient Crowd Counting , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).