DANet: Enhancing Small Object Detection through an Efficient Deformable Attention Network

TL;DR

This paper introduces DANet, a novel network combining deformable convolutions, attention mechanisms, and multi-scale features to improve small object detection accuracy in manufacturing and general datasets.

Contribution

The paper presents DANet, integrating deformable convolutions, attention modules, and Focal Loss with Faster R-CNN for enhanced small object detection.

Findings

Achieved state-of-the-art accuracy on NEU-DET defect dataset.

Demonstrated strong generalization on Pascal VOC dataset.

Improved detection of small and complex objects.

Abstract

Efficient and accurate detection of small objects in manufacturing settings, such as defects and cracks, is crucial for ensuring product quality and safety. To address this issue, we proposed a comprehensive strategy by synergizing Faster R-CNN with cutting-edge methods. By combining Faster R-CNN with Feature Pyramid Network, we enable the model to efficiently handle multi-scale features intrinsic to manufacturing environments. Additionally, Deformable Net is used that contorts and conforms to the geometric variations of defects, bringing precision in detecting even the minuscule and complex features. Then, we incorporated an attention mechanism called Convolutional Block Attention Module in each block of our base ResNet50 network to selectively emphasize informative features and suppress less useful ones. After that we incorporated RoI Align, replacing RoI Pooling for finer region-of-interest alignment and finally the integration of Focal Loss effectively handles class imbalance, crucial for rare defect occurrences. The rigorous evaluation of our model on both the NEU-DET and Pascal VOC datasets underscores its robust performance and generalization capabilities. On the NEU-DET dataset, our model exhibited a profound understanding of steel defects, achieving state-of-the-art accuracy in identifying various defects. Simultaneously, when evaluated on the Pascal VOC dataset, our model showcases its ability to detect objects across a wide spectrum of categories within complex and small scenes.