Collaborative Descriptors: Convolutional Maps for Preprocessing
This addresses the problem of enhancing feature representation in computer vision, though it appears incremental as it builds on existing methods.
The paper tackled the problem of improving object recognition and detection by combining deeply learned and hand-crafted features using convolutional maps for preprocessing, resulting in performance increases of +17.06% for multi-class object recognition and +24.71% for car detection.
The paper presents a novel concept for collaborative descriptors between deeply learned and hand-crafted features. To achieve this concept, we apply convolutional maps for pre-processing, namely the convovlutional maps are used as input of hand-crafted features. We recorded an increase in the performance rate of +17.06 % (multi-class object recognition) and +24.71 % (car detection) from grayscale input to convolutional maps. Although the framework is straight-forward, the concept should be inherited for an improved representation.