Small object detection is the task of detecting small objects.
( Image credit: Feature-Fused SSD )
As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task.
#10 best model for Instance Segmentation on COCO test-dev
Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance.
In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet.
We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects.
We evaluate different pasting augmentation strategies, and ultimately, we achieve 9. 7\% relative improvement on the instance segmentation and 7. 1\% on the object detection of small objects, compared to the current state of the art method on
The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps.