Fast Algorithms for Convolutional Neural Networks
Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We introduce a new class of fast algorithms for convolutional neural networks using Winograd's minimal filtering algorithms. The algorithms compute minimal complexity convolution over small tiles, which makes them fast with small filters and small batch sizes. We benchmark a GPU implementation of our algorithm with the VGG network and show state of the art throughput at batch sizes from 1 to 64.
Code (5)
Tasks
GPUPedestrian DetectionSelf-Driving CarsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Application of Faster R-CNN model on Human Running Pattern Recognition
The advance algorithms like Faster Regional Convolutional Neural Network (Faster R-CNN) models are suitable to identify classified moving objects, due to the efficiency in learning the training dataset superior than ordi…
Object RecognitionFast Spectrogram Inversion using Multi-head Convolutional Neural Networks
We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN …
speech-recognitionSpeech RecognitionSpeech SynthesisRelief R-CNN : Utilizing Convolutional Features for Fast Object Detection
R-CNN style methods are sorts of the state-of-the-art object detection methods, which consist of region proposal generation and deep CNN classification. However, the proposal generation phase in this paradigm is usually …
object-detectionObject DetectionReal-Time Object DetectionRegion ProposalSimple Fast Convolutional Feature Learning
The quality of the features used in visual recognition is of fundamental importance for the overall system. For a long time, low-level hand-designed feature algorithms as SIFT and HOG have obtained the best results on im…
Efficient Algorithms for Convolutional Inverse Problems in Multidimensional Imaging
Multidimensional imaging, capturing image data in more than two dimensions, has been an emerging field with diverse applications. Due to the limitation of two-dimensional detectors in obtaining the high-dimensional image…
Image Reconstruction