ThumbNet: One Thumbnail Image Contains All You Need for Recognition

Chen Zhao, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Although deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks, its real-world application is still impeded by its voracious demand of computational resources. Current works mostly seek to compress the network by reducing its parameters or parameter-incurred computation, neglecting the influence of the input image on the system complexity. Based on the fact that input images of a CNN contain substantial redundancy, in this paper, we propose a unified framework, dubbed as ThumbNet, to simultaneously accelerate and compress CNN models by enabling them to infer on one thumbnail image. We provide three effective strategies to train ThumbNet. In doing so, ThumbNet learns an inference network that performs equally well on small images as the original-input network on large images. With ThumbNet, not only do we obtain the thumbnail-input inference network that can drastically reduce computation and memory requirements, but also we obtain an image downscaler that can generate thumbnail images for generic classification tasks. Extensive experiments show the effectiveness of ThumbNet, and demonstrate that the thumbnail-input inference network learned by ThumbNet can adequately retain the accuracy of the original-input network even when the input images are downscaled 16 times.
Original languageEnglish (US)
Title of host publicationProceedings of the 28th ACM International Conference on Multimedia
PublisherACM
ISBN (Print)9781450379885
DOIs
StatePublished - Oct 12 2020

Fingerprint

Dive into the research topics of 'ThumbNet: One Thumbnail Image Contains All You Need for Recognition'. Together they form a unique fingerprint.

Cite this