OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
This work addresses the problem of unified visual recognition tasks for computer vision applications, representing a novel integrated approach rather than incremental.
The paper tackles integrated object recognition, localization, and detection using convolutional networks, achieving winner status in the ImageNet 2013 localization challenge and establishing a new state-of-the-art in detection.
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.