Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Multi-Scale Dense Networks for Resource Efficient Image Classification
Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Weinberger
Feb 15, 2018 (modified: Feb 23, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network’s prediction for a test example is progressively updated, facilitating the output of a prediction at any time; and 2. budgeted batch classification, where a fixed amount of computation is available to classify a set of examples that can be spent unevenly across “easier” and “harder” inputs. In contrast to most prior work, such as the popular Viola and Jones algorithm, our approach is based on convolutional neural networks. We train multiple classifiers with varying resource demands, which we adaptively apply during test time. To maximally re-use computation between the classifiers, we incorporate them as early-exits into a single deep convolutional neural network and inter-connect them with dense connectivity. To facilitate high quality classification early on, we use a two-dimensional multi-scale network architecture that maintains coarse and fine level features all-throughout the network. Experiments on three image-classification tasks demonstrate that our framework substantially improves the existing state-of-the-art in both settings.
Keywords:efficient learning, budgeted learning, deep learning, image classification, convolutional networks
Enter your feedback below and we'll get back to you as soon as possible.