PVANet swMATH ID: 28335 Software Authors: Kye-Hyeon Kim, Sanghoon Hong, Byungseok Roh, Yeongjae Cheon, Minje Park Description: PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection. This paper presents how we can achieve the state-of-the-art accuracy in multi-category object detection task while minimizing the computational cost by adapting and combining recent technical innovations. Following the common pipeline of ”CNN feature extraction + region proposal + RoI classification”, we mainly redesign the feature extraction part, since region proposal part is not computationally expensive and classification part can be efficiently compressed with common techniques like truncated SVD. Our design principle is ”less channels with more layers” and adoption of some building blocks including concatenated ReLU, Inception, and HyperNet. The designed network is deep and thin and trained with the help of batch normalization, residual connections, and learning rate scheduling based on plateau detection. We obtained solid results on well-known object detection benchmarks: 83.8 Homepage: https://arxiv.org/abs/1608.08021 Source Code: https://github.com/sanghoon/pva-faster-rcnn Related Software: Caffe; ImageNet; AlexNet; XNOR-Net; Inception-v4; DoReFa-Net; SqueezeNet; MobileNets; MS-COCO; ShuffleNet; Faster R-CNN; SSD; fbfft; cuda-convnet; LCNN; TensorFlow; Xception; DOTA; LabelMe; PASCAL VOC Cited in: 3 Publications all top 5 Cited by 15 Authors 1 Bai, Xiang 1 Chen, Yurong 1 Dong, Yinpeng 1 Fieguth, Paul W. 1 Li, Jianguo 1 Liao, Minghui 1 Liu, Li 1 Liu, Xinwang 1 Ni, Renkun 1 Ouyang, Wanli 1 Pietikäinen, Matti 1 Shi, Baoguang 1 Su, Hang 1 Wang, Xiaogang 1 Zhu, Jun Cited in 2 Serials 2 International Journal of Computer Vision 1 IEEE Transactions on Image Processing Cited in 2 Fields 2 Computer science (68-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year