Augmentation for small object detection
In recent years, object detection has experienced impressive progress. Despite these improvements, there is still a significant gap in the performance between the detection of small and large objects. We analyze the current state-of-the-art model, Mask-RCNN, on a challenging dataset, MS COCO. We show that the overlap between small ground-truth objects and the predicted anchors is much lower than the expected IoU threshold. We conjecture this is due to two factors; (1) only a few images are containing small objects, and (2) small objects do not appear enough even within each image containing them. We thus propose to oversample those images with small objects and augment each of those images by copy-pasting small objects many times. It allows us to trade off the quality of the detector on large objects with that on 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 MS COCO.
Code (5)
Tasks
Instance SegmentationObjectobject-detectionObject DetectionSemantic SegmentationSmall Object DetectionSimilar Papers 제목 키워드 기반
Data Augmentation For Small Object using Fast AutoAugment
In recent years, there has been tremendous progress in object detection performance. However, despite these advances, the detection performance for small objects is significantly inferior to that of large objects. Detect…
Data AugmentationObjectobject-detectionObject DetectionSelect-Mosaic: Data Augmentation Method for Dense Small Object Scenes
Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the…
Data AugmentationDiversityobject-detectionObject Detection+1Chosen methods of improving small object recognition with weak recognizable features
Many object detection models struggle with several problematic aspects of small object detection including the low number of samples, lack of diversity and low features representation. Taking into account that GANs belon…
DiversityObjectobject-detectionObject Detection+2Single-stage uav detection and classification with yolov5: Mosaic data augmentation and panet
In Drone-vs-Bird Detection Challenge in conjunction with the 4th International Workshop on Small-Drone Surveillance, Detection and Counteraction Techniques at IEEE AVSS 2021, we proposed a YOLOV5-based object detection m…
2D Object DetectionData Augmentationobject-detectionObject DetectionSmall Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion
The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object dete…
Objectobject-detectionObject DetectionReal-Time Object Detection+1