Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible. Such loss of spatial acuity can limit image classification accuracy and complicate the transfer of the model to downstream applications that require detailed scene understanding. These problems can be alleviated by dilation, which increases the resolution of output feature maps without reducing the receptive field of individual neurons...
Authors
Related Content
Network Sketching: Exploiting Binary Structure in Deep CNNs
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks. However, deep networks are...
Accurate Optical Flow via Direct Cost Volume Processing
We present an optical flow estimation approach that operates on the full four-dimensional cost volume. This direct approach shares the...
Physics Inspired Optimization on Semantic Transfer Features: An...
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes. This method enjoys the...
RON: Reverse Connection with Objectness Prior Networks for...
We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best...