# Small target detection algorithm based on multi-branch stacking and new sampling transition module

## TL;DR

This paper introduces AMT-SSD, a new algorithm that improves small target detection by using multi-branch stacking and an attention-based sampling module.

## Contribution

The novel AMT-SSD algorithm combines multi-branch stacking and an attention-based sampling transition module to enhance small target detection.

## Key findings

- AMT-SSD achieves 84.6% mAP on the PASCAL VOC dataset.
- The algorithm reaches 53.4% mAP on the MS COCO dataset.
- The new modules effectively reduce feature loss during detection.

## Abstract

Aiming at the problem that the SSD algorithm does not fully extract the feature information contained in each feature layer, as well as the feature information is easily lost during the sampling process, which makes the feature expression ineffective and leads to insufficient performance in small target detection. In this paper, AMT-SSD is proposed, a small target detection algorithm that incorporates the multi-branch stacking and new sampling transition module of the attention mechanism. In this algorithm, the composite attention mechanism is utilized to improve the correlation of features of the samples to be detected in terms of spatial and channels, and the efficiency of the algorithm; secondly, multi-branch stacking module is used to extract multi-size features for each feature layer, and different sizes of convolution kernels are utilized in parallel to fully extract their features and improve the expression of features; meanwhile, during the sampling process, the problem of missing features is solved by applying inverse subpixel convolution in the new sampling transition module. Experimentally, the AMT-SSD algorithm achieves 84.6% and 53.4% mAP metrics on the PASCAL VOC dataset and MS COCO dataset, respectively. This indicates that the AMT-SSD algorithm can effectively extract feature information that is beneficial to detection samples, and also performs well in reducing feature loss, which is effective for the algorithm to improve the algorithm on small targets.