Fish Image Instance Segmentation : An Enhanced Hybrid Task Cascade Approach

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 15th International Conference on Semantic Computing
Subtitle of host publicationICSC 2021
PublisherIEEE
Pages306-313
ISBN (Electronic)9781728188997
ISBN (Print)9781728189000
Publication statusPublished - Jan 2021

Publication series

NameProceedings - IEEE International Conference on Semantic Computing, ICSC
ISSN (Print)2325-6516

Conference

Title15th IEEE International Conference on Semantic Computing (ICSC 2021)
LocationVirtual
PlaceUnited States
CityLaguna Hills
Period27 - 29 January 2021

Abstract

The fish instance segmentation task plays an important role in fish image analysis. Traditional fish analysis methods (e.g., segmenting the fish curve by hand to obtain the size of fish) cost a mass of manual labor and thus are not efficient. Convolutional Neural Networks (CNNs) become an effective scheme to replace manual labor to decrease costs and improve efficiency. The Hybrid Task Cascade (HTC) is a novel CNN model which applies cascade architecture to achieve boosted performance in the instance segmentation task. However, instance segmentation models cannot handle fish images very well due to small image size and low image quality. Furthermore, HTC still suffers from the incomplete confidence score only consisting of the classification information without the mask information, so the instance segmentation performance would be degraded. To this end, we propose an Enhanced Hybrid Task Cascade (EHTC) model to overcome these limitations. (1) The EHTC conducts data pre-processing before the instance segmentation network through an image super-resolution technology to resize images and optimize features that can be more easily understood by the later instance segmentation network. (2) Our EHTC addresses the incomplete confidence score problem in the HTC by adding one mask scoring block, named MaskIoU, to generate mask confidence scores providing the mask that improves the instance segmentation accuracy. Finally, the experimental results show that our EHTC achieves better performance than the state-of-the-art models on the Fish4knowledge dataset.

Research Area(s)

  • Enhanced Hybrid Task Cascade, feature enhancement, Fish instance segmentation, mask evaluation

Citation Format(s)

Fish Image Instance Segmentation : An Enhanced Hybrid Task Cascade Approach. / Zhang, Tian-Tian; Chow, Chi-Yin; Zhang, Jia-Dong.

Proceedings - 2021 IEEE 15th International Conference on Semantic Computing: ICSC 2021. IEEE, 2021. p. 306-313 9364515 (Proceedings - IEEE International Conference on Semantic Computing, ICSC).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review