ELASTIC: Improving CNNs With Dynamic Scaling Policies

By Huiyu Wang, Aniruddha Kembhavi, Ali Farhadi, Alan L. Yuille, Mohammad Rastegari. 2018

64 citations recorded by the source corpus.

Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have a similar theme: a set of intuitive and manually designed policies that are generic and fixed (e.g. SIFT or feature pyramid). We argue that the scaling policy should be learned from data. In this paper, we introduce Elastic, a simple, efficient and yet very effective approach to learn a dynamic scale policy from data. We formulate the scaling policy as a non-linear function inside the network's structure that (a) is learned from data, (b) is instance specific, (c) does not add extra computation, and (d) can be applied on any network architecture. We applied Elastic to several state-of-the-art network architectures and showed consistent improvement without extra (sometimes even lower) computation on ImageNet classification, MSCOCO multi-label classification, and PASCAL VOC semantic segmentation. Our results show major improvement for images with scale challenges. Our code is available here: https://github.com/allenai/elastic

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Efficiency & Compression

Citations in the corpus

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “Some employ atrous convolutions [34,77,67,13], larger kernel [70], or image pyramids [98,85], either designed by hand or searched by algorithms [103,12,60].”
Dynamic Neural Networks: A Survey (2021, background): “For instance, Elastic [165] realizes a soft selection from multiple branches at every layer, where each branch performs a downsample-convolutionupsample procedure with an independent scaling ratio.”
CSPNet: A New Backbone that can Enhance Learning Capability of CNN (2019, methodology): “We apply the proposed CSPNet to ResNet-10 [7], ResNeXt-50 [39], PeleeNet [37], and DenseNet-201-Elastic [36] and compare with state-of-the-art methods.”