SCAResNet: A ResNet Variant Optimized for Tiny Object Detection in Transmission and Distribution Towers.

Traditional deep-learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to facilitate model propagation and fully connected classification. However, resizing inevitably leads to object deformation and loss of valuable information in the images. This drawback becomes particularly pronounced for tiny objects such as distribution towers (DTs) with linear shapes and few pixels. To address this issue, we propose abandoning the resizing operation. Instead, we introduce positional-encoding multihead criss-cross attention (CCA). This allows the model to capture contextual information and learn from multiple representation subspaces, effectively enriching the semantics of DTs. In addition, we enhance spatial pyramid pooling by reshaping three pooled feature maps into a new unified one while also reducing the computational burden. This approach allows images of different sizes and scales to generate feature maps with uniform dimensions and can be used in feature map propagation. Our SCAResNet incorporates these aforementioned improvements into the backbone network ResNet. We evaluated our SCAResNet using the electric transmission and distribution infrastructure imagery (ETDII) dataset from Duke University. Without any additional tricks, we used various object detection models with Gaussian receptive-field-based label assignment (RFLA) as the baseline. When incorporating the SCAResNet into the baseline model, we achieved a 2.1% improvement in mAPs. This demonstrates the advantages of our SCAResNet in detecting transmission and DTs and its value in tiny object detection (TOD). The source code is available at https://github.com/LisavilaLee/SCAResNet_mmdet. [ABSTRACT FROM AUTHOR]