ScaleNet - Improve CNNs through Recursively Rescaling Objects

Authors

  • Xingyi Li Oregon State University
  • Zhongang Qi Tencent
  • Xiaoli Fern Oregon State University
  • Fuxin Li Oregon State University

DOI:

https://doi.org/10.1609/aaai.v34i07.6806

Abstract

Deep networks are often not scale-invariant hence their performance can vary wildly if recognizable objects are at an unseen scale occurring only at testing time. In this paper, we propose ScaleNet, which recursively predicts object scale in a deep learning framework. With an explicit objective to predict the scale of objects in images, ScaleNet enables pretrained deep learning models to identify objects in the scales that are not present in their training sets. By recursively calling ScaleNet, one can generalize to very large scale changes unseen in the training set. To demonstrate the robustness of our proposed framework, we conduct experiments with pretrained as well as fine-tuned classification and detection frameworks on MNIST, CIFAR-10, and MS COCO datasets and results reveal that our proposed framework significantly boosts the performances of deep networks.

Downloads

Published

2020-04-03

How to Cite

Li, X., Qi, Z., Fern, X., & Li, F. (2020). ScaleNet - Improve CNNs through Recursively Rescaling Objects. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11426-11433. https://doi.org/10.1609/aaai.v34i07.6806

Issue

Section

AAAI Technical Track: Vision