Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

July 10, 2018 · Entered Twilight · 🏛 International Conference on Learning Representations

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: CONTRIBUTING.md, LICENSE, MAINTAINERS.md, README.md, imagenet-train.py, imagenet_utils.py, models, requirement.txt

Authors Chun-Fu Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogerio Feris arXiv ID 1807.03848 Category cs.CV: Computer Vision Citations 100 Venue International Conference on Learning Representations Repository https://github.com/IBM/BigLittleNet ⭐ 58 Last Checked 2 months ago

Abstract

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains. The codes are available at https://github.com/IBM/BigLittleNet