From generic to specific deep representations for visual recognition

Evidence is mounting that CNNs are currently the most efficient and successful way to learn visual representations. This paper address the questions on why CNN representations are so effective and how to improve them if one wants to maximize performance for a single task or a range of tasks. We assess experimentally the importance of different aspects of learning and choosing a CNN representation to its performance on a diverse set of visual recognition tasks. In particular, we investigate how altering the parameters in a network’s architecture and its training impacts the representation’s ability to specialize and generalize. We also study the effect of fine-tuning a generic network towards a particular task. Extensive exper-iments indicate the trends; (a) increasing specialization increases performance on the target task but can hurt the ability to generalize to other tasks and (b) the less specialized the original network the more likely it is to benefit from fine-tuning. As by-products we have learnt several deep CNN image representations which when combined with a simple linear SVM classifier or similarity measure pro-duce the best performance on 12 standard datasets measuring the ability to solve visual recognition tasks ranging from image classification to image retrieval.