Deep Multi-Context Network For Fine-Grained Visual Recognition

In this paper, we tackle the FINE-GRAINED VISUAL RECOGNITION problem by proposing a deep multi-context framework. We employ deep Convolutional Neural Networks to model features of objects in images. Global context and local context are both taken into consideration, and are jointly modeled in a unified multi-context deep learning framework. To cleanse the relatively dirty data for training, a regional proposal method is designed to make the multi-context modeling suited for fine-grained visual recognition in the real world. Furthermore, recently proposed contemporary deep models are used, and their combination is investigated. Our approaches are evaluated on MSR-IRC 2016 and further assessed on the more complex validation set. The results show significant and consistent improvements over the baseline.