Αποθηκεύτηκε σε:
| Κύριοι συγγραφείς: | , , , , |
|---|---|
| Μορφή: | Preprint |
| Έκδοση: |
2019
|
| Θέματα: | |
| Διαθέσιμο Online: | https://arxiv.org/abs/1908.08652 |
| Ετικέτες: |
Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
|
| _version_ | 1866913793353711616 |
|---|---|
| author | Kumar, Abhay Jain, Nishant Tripathi, Suraj Singh, Chirag Krishna, Kamal |
| author_facet | Kumar, Abhay Jain, Nishant Tripathi, Suraj Singh, Chirag Krishna, Kamal |
| contents | We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model has two related tasks, with Crowd Density Estimation as the main task and Crowd-Count Group Classification as the auxiliary task. The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task. The main task model comprises two blocks: VGG-16 front-end for feature extraction and a dilated Convolutional Neural Network for density map generation. The auxiliary task model shares the same front-end as the main task, followed by a CNN classifier. Our proposed network achieves 5.8% and 14.9% lower Mean Absolute Error (MAE) than the state-of-the-art methods on ShanghaiTech dataset without using any data augmentation. Our model also outperforms with 10.5% lower MAE on UCF_CC_50 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1908_08652 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation Kumar, Abhay Jain, Nishant Tripathi, Suraj Singh, Chirag Krishna, Kamal Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model has two related tasks, with Crowd Density Estimation as the main task and Crowd-Count Group Classification as the auxiliary task. The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task. The main task model comprises two blocks: VGG-16 front-end for feature extraction and a dilated Convolutional Neural Network for density map generation. The auxiliary task model shares the same front-end as the main task, followed by a CNN classifier. Our proposed network achieves 5.8% and 14.9% lower Mean Absolute Error (MAE) than the state-of-the-art methods on ShanghaiTech dataset without using any data augmentation. Our model also outperforms with 10.5% lower MAE on UCF_CC_50 dataset. |
| title | MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/1908.08652 |