Small Object Detection using Context and Attention
This work addresses the specific problem of small object detection for computer vision applications, but it appears incremental as it builds upon existing methods like SSD with added context and attention features.
The authors tackled the problem of detecting small objects in images, which is challenging due to low resolution and limited information, and achieved a result of 78.1% mAP on the PASCAL VOC2007 test set using a method that incorporates context and attention mechanisms.
There are many limitations applying object detection algorithm on various environments. Especially detecting small objects is still challenging because they have low resolution and limited information. We propose an object detection method using context for improving accuracy of detecting small objects. The proposed method uses additional features from different layers as context by concatenating multi-scale features. We also propose object detection with attention mechanism which can focus on the object in image, and it can include contextual information from target layer. Experimental results shows that proposed method also has higher accuracy than conventional SSD on detecting small objects. Also, for 300$\times$300 input, we achieved 78.1% Mean Average Precision (mAP) on the PASCAL VOC2007 test set.