arXiv:1412.7755cs.LG
Multiple Object Recognition with Visual Attention
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image. We show that the model learns to both localize and recognize multiple objects despite being given only class labels during training. We evaluate the model on the challenging task of transcribing house number sequences from Google Street View images and show that it is both more accurate than the state-of-the-art convolutional networks and uses fewer parameters and less computation.
This would be quite a cool problem to attack using RNN. Perhaps using an attention-following mechanism like the one used for house numbers [1]. It's fairly well-defined. You would need a ton of example data though. [1] http://arxiv.org/abs/1412.7755
radarsat1View on HNParent context