Deep Convolutional Neural Networks (CNNs) have been repeatedly proven to perform well on image classification tasks. Object detection methods, however, are still in need of significant improvements. In this paper, we propose a new framework called Ventral-Dorsal Networks (VDNets) which is inspired by the structure of the human visual system. Roughly, the visual input signal is analyzed along two separate neural streams, one in the temporal lobe and the other in the parietal lobe. The coarse functional distinction between these streams is between object recognition — the “what” of the signal – and extracting location related information — the “where” of the signal. The ventral pathway from primary visual cortex, entering the temporal lobe, is dominated by “what” information, while the dorsal pathway, into the parietal lobe, is dominated by “where” information. Inspired by this structure, we propose the integration of a “Ventral Network” and a “Dorsal Network”, which are complementary. Information about object identity can guide localization, and location information can guide attention to relevant image regions, improving object recognition. This new dual network framework sharpens the focus of object detection. Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches on PASCAL VOC 2007 by 8% (mAP) and PASCAL VOC 2012 by 3% (mAP). Moreover, a comparison of techniques on Yearbook images displays substantial qualitative and quantitative benefits of VDNet.
|Title of host publication||Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||9|
|Publication status||Published - 2019 Mar 4|
|Event||19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 - Waikoloa Village, United States|
Duration: 2019 Jan 7 → 2019 Jan 11
|Name||Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019|
|Conference||19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019|
|Period||19/1/7 → 19/1/11|
Bibliographical noteFunding Information:
This work was started as an internship research project at Ancestry.com Operations Inc. and continued at UC Merced. We would like to thank Ancestry.com Operations Inc. data science division for useful discussions and providing computational GPU resources.
© 2019 IEEE
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Computer Science Applications