Journal
NEUROCOMPUTING
Volume 423, Issue -, Pages 490-505Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2020.10.075
Keywords
Deep Learning; Computer Vision; Convolutional Neural Networks; Object Detection; Instance Segmentation
Categories
Funding
- NVIDIA Corporation
Ask authors/readers for more resources
CentroidNetV2 is a novel hybrid Convolutional Neural Network specifically designed to segment and count many small and connected object instances. It achieves high-quality centroids and borders of object instances by decoding centroid votes and border votes, using a loss function that combines cross-entropy loss and Euclidean-distance loss.
This paper presents CentroidNetV2, a novel hybrid Convolutional Neural Network (CNN) that has been specifically designed to segment and count many small and connected object instances. This complete redesign of the original CentroidNet uses a CNN backbone to regress a field of centroid-voting vectors and border-voting vectors. The segmentation masks of the individual object instances are produced by decoding centroid votes and border votes. A loss function that combines cross-entropy loss and Euclidean-distance loss achieves high quality centroids and borders of object instances. Several backbones and loss functions are tested on three different datasets ranging from precision agriculture to microbiology and pathology. CentroidNetV2 is compared to the state-of-the art networks You Only Look Once Version 3 (YOLOv3) and Mask Recurrent Convolutional Neural Network (MRCNN). On two out of three datasets CentroidNetV2 achieves the highest F1 score and on all three datasets CentroidNetV2 achieves the highest recall. CentroidNetV2 demonstrates the best ability to detect small objects although the best segmentation masks for larger objects are produced by MRCNN. (c) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available