Learning Smooth Pooling Regions for Visual Recognition
By Mateusz Malinowski, Mario Fritz. 2013
28 citations recorded by the source corpus.
From the early HMAX model to Spatial Pyramid Matching, spatial pooling has played an important role in visual recognition pipelines. By aggregating local statistics, it equips the recognition pipelines with a certain degree of robustness to translation and deformation yet preserving spatial information. Despite of its predominance in current recognition systems, we have seen little progress to fully adapt the pooling strategy to the task at hand. In this paper, we propose a flexible parameterization of the spatial pooling step and learn the pooling regions together with the classifier. We investigate a smoothness regularization term that in conjuncture with an efficient learning scheme makes learning scalable. Our framework can work with both popular pooling operators: sum-pooling and max-pooling. Finally, we show benefits of our approach for object recognition tasks based on visual words and higher level event recognition tasks based on object-bank features. In both cases, we improve over the hand-crafted spatial pooling step showing the importance of its adaptation to the task.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Edouard Oyallon
- Mateusz Malinowski
- Stéphane Mallat
- Mario Fritz
- Victor S. Lempitsky
- Trevor Darrell
- Kate Saenko
- Vadim Lebedev
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Andrea Vedaldi
- Dacheng Tao
- Xiaogang Wang
- Andrew Zisserman
- Ming-Hsuan Yang
- Jitendra Malik
Citations in the corpus
- Fast ConvNets Using Group-Wise Brain Damage (2015, background): “The combination of sparsity and deep learning has been investigated within several unsupervised approaches such as sparse autoencoders [3, 5] and sparse deep belief networks [27].”
- Deep roto-translation scattering for object classification (2014, methodology): “We reported the result on CIFAR100 from [10] via [20].”
- A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation (2014, methodology): “1, spatial templates fit into a spatial pooling regions framework [18] by fusing ideas of learning pooling operators [21] with object-centrism [27].”
- Deep Decision Network for Multi-class Image Classification (2016, unknown): “Learned Pooling[17] 43.”