Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
This work addresses efficiency for object detection in computer vision, offering an incremental improvement by integrating attention mechanisms to reduce computational costs.
The paper tackles the problem of high computational complexity in object detectors by introducing the Selective Convolutional Network (SCN), which selectively processes only meaningful locations to ignore background areas, resulting in a reduction of calculations by 1/5 to 1/3 with slight accuracy loss on PASCAL VOC2007 and MS COCO datasets.
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt at attention. Therefore, we introduce an efficient object detector called Selective Convolutional Network (SCN), which selectively calculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature extraction. To solve it, we design an elaborate structure with negligible overheads to guide the network where to look next. It's end-to-end trainable and easy-embedding. Without additional segmentation datasets, we explores two different train strategies including direct supervision and indirect supervision. Extensive experiments assess the performance on PASCAL VOC2007 and MS COCO detection datasets. Results show that SSD and Pelee integrated with our method averagely reduce the calculations in a range of 1/5 and 1/3 with slight loss of accuracy, demonstrating the feasibility of SCN.