Coral Reef Annotation, Localisation and Pixel-wise Classification using Mask-RCNN and Bag of Tricks

This article describes an automatic system for detection, classification and segmentation of individual coral substrates in underwater images. The proposed system achieved the best performances in both tasks of the second edition of the ImageCLEFcoral competition. Specifically, mean average precision with Intersection over Union (IoU) greater then 0.5 (mAP@0.5) of 0.582 in case of Coral reef image annotation and localisation, and mAP@0.5 of 0.678 in Coral reef image pixel-wise parsing. The system is based on Mask R-CNN object detection and instance segmentation framework boosted by advanced training strategies, pseudo-labeling, test-time augmentations, and Accumulated Gradient Normalisation. To support future research, code has been made available at: https://github.com/picekl/ImageCLEF2020-DrawnUI.

[1]  Cha Zhang,et al.  Ensemble Machine Learning: Methods and Applications , 2012 .

[2]  Antonio C. de A. Campello,et al.  Overview of the ImageCLEFcoral 2020 Task: Automated Coral Reef Image Annotation , 2020, CLEF.

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kaiming He,et al.  Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour , 2017, ArXiv.

[5]  Importance of live coral habitat for reef fishes , 2014, Reviews in Fish Biology and Fisheries.

[6]  Reka Hollandi,et al.  Test-time augmentation for deep learning-based cell segmentation on microscopy images , 2019, Scientific Reports.

[7]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[8]  Gerasimos Spanakis,et al.  Accumulated Gradient Normalization , 2017, ACML.

[9]  Lucas Beyer,et al.  Big Transfer (BiT): General Visual Representation Learning , 2020, ECCV.

[10]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[11]  C. Birkeland,et al.  Global Status of Coral Reefs: In Combination, Disturbances and Stressors Become Ratchets , 2019, World Seas: an Environmental Evaluation.

[12]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Minh-Triet Tran,et al.  Overview of the ImageCLEF 2020: Multimedia Retrieval in Medical, Lifelogging, Nature, and Internet Applications , 2020, CLEF.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[16]  Jiri Matas,et al.  Recognition of the Amazonian flora by InceptionNetworks with Test-time Class Prior Estimation , 2019, CLEF.

[17]  Jiri Matas,et al.  Plant Recognition by Inception Networks with Test-time Class Prior Estimation , 2018, CLEF.

[18]  Graham W. Taylor,et al.  Improved Regularization of Convolutional Neural Networks with Cutout , 2017, ArXiv.

[19]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[20]  Luke Brander,et al.  The Economic Impact of Ocean Acidification on Coral Reefs , 2012 .