Listwise View Ranking for Image Cropping
Preprint
Abstract
Rank-based Learning with deep neural network has been widely used for image cropping. However, the performance of ranking-based methods is often poor and this is mainly due to two reasons: 1) image cropping is a listwise ranking task rather than pairwise comparison; 2) the rescaling caused by pooling layer and the deformation in view generation damage the performance of composition learning. In this paper, we develop a novel model to overcome these problems. To address the first problem, we formulate the image cropping as a listwise ranking problem to find the best view composition. For the second problem, a refined view sampling (called RoIRefine) is proposed to extract refined feature maps for candidate view generation. Given a series of candidate views, the proposed model learns the Top-1 probability distribution of views and picks up the best one. By integrating refined sampling and listwise ranking, the proposed network called LVRN achieves the state-of-the-art performance both in accuracy and speed.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping2018
- Learning to Compose with Professional Photographs on the Web2017
- Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study2017
- Photo Aesthetics Ranking Network with Attributes and Content Adaptation2016
- Automatic Image Cropping using Visual Composition, Boundary Simplicity and Content Preservation Models2014
- A framework for visual saliency detection with applications to image thumbnailing2009
- Self-Adaptive Image Cropping for Small DisplaysIEEE Transactions on Consumer Electronics, 2007