Corpus ID: 55687967

ELASTIC: Improving CNNs with Instance Specific Scaling Policies

  title={ELASTIC: Improving CNNs with Instance Specific Scaling Policies},
  author={Huiyu Wang and Aniruddha Kembhavi and Ali Farhadi and A. Yuille and Mohammad Rastegari},
Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have 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 scale policy should be learned from data. In this paper, we introduce ELASTIC, a simple, efficient and yet very effective approach to learn instance-specific scale policy from data. We formulate the scaling policy as a non… Expand
5 Citations
DiCENet: Dimension-wise Convolutions for Efficient Networks
  • 4
  • PDF
Multi-Dimensional Pruning: A Unified Framework for Model Compression
  • 1
  • PDF
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution
  • 146
  • Highly Influenced
  • PDF


Feature Pyramid Networks for Object Detection
  • 5,570
  • PDF
Aggregated Residual Transformations for Deep Neural Networks
  • 3,423
  • Highly Influential
  • PDF
ParseNet: Looking Wider to See Better
  • 699
  • PDF
Multilabel Image Classification With Regional Latent Semantic Dependencies
  • 72
  • PDF
Rethinking Atrous Convolution for Semantic Image Segmentation
  • 2,257
  • PDF
Improving Pairwise Ranking for Multi-label Image Classification
  • Y. Li, Yale Song, Jiebo Luo
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 109
  • PDF
Rethinking the Inception Architecture for Computer Vision
  • 10,636
  • PDF
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
  • 86
  • PDF
Hypercolumns for object segmentation and fine-grained localization
  • 1,209
  • PDF