Half-CNN: A General Framework for Whole-Image Regression
This provides a generic regression framework for applications like object detection and segmentation, avoiding manual classifier design, but it is incremental as it builds on existing CNN structures.
The authors tackled the problem of whole-image regression by proposing a CNN framework that removes the full connection layer and trains with continuous feature maps, achieving results comparable to other models in face detection & segmentation and scene saliency prediction using a small-scale network.
The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this paper, we propose a whole-image CNN regression model, by removing the full connection layer and training the network with continuous feature maps. This is a generic regression framework that fits many applications. We demonstrate this method through two tasks: simultaneous face detection & segmentation, and scene saliency prediction. The result is comparable with other models in the respective fields, using only a small scale network. Since the regression model is trained on corresponding image / feature map pairs, there are no requirements on uniform input size as opposed to the classification model. Our framework avoids classifier design, a process that may introduce too much manual intervention in model development. Yet, it is highly correlated to the classification network and offers some in-deep review of CNN structures.