An Empirical Study on Ensemble of Segmentation Approaches
Open Access
Abstract
Recognizing objects in images requires complex skills that involve knowledge about the context and the ability to identify the borders of the objects. In computer vision, this task is called semantic segmentation and it pertains to the classification of each pixel in an image. The task is of main importance in many real-life scenarios: in autonomous vehicles, it allows the identification of objects surrounding the vehicle; in medical diagnosis, it improves the ability of early detecting of dangerous pathologies and thus mitigates the risk of serious consequences. In this work, we propose a new ensemble method able to solve the semantic segmentation task. The model is based on convolutional neural networks (CNNs) and transformers. An ensemble uses many different models whose predictions are aggregated to form the output of the ensemble system. The performance and quality of the ensemble prediction are strongly connected with some factors; one of the most important is the diversity among individual models. In our approach, this is enforced by adopting different loss functions and testing different data augmentations. We developed the proposed method by combining DeepLabV3+, HarDNet-MSEG, and Pyramid Vision Transformers. The developed solution was then assessed through an extensive empirical evaluation in five different scenarios: polyp detection, skin detection, leukocytes recognition, environmental microorganism detection, and butterfly recognition. The model provides state-of-the-art results.Keywords
This publication has 54 references indexed in Scilit:
- Learning Deconvolution Network for Semantic Segmentation2015
- WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physiciansComputerized Medical Imaging and Graphics, 2015
- Self-adaptive algorithm for segmenting skin regionsEURASIP Journal on Advances in Signal Processing, 2014
- Skin detection by dual maximization of detectors agreement for video monitoringPattern Recognition Letters, 2013
- Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancerInternational Journal of Computer Assisted Radiology and Surgery, 2013
- Towards automatic polyp detection with a polyp appearance modelPattern Recognition, 2012
- Learning Models for Object Recognition from Natural Language Descriptions2009
- Objective evaluation of approaches of skin detection using ROC analysisComputer Vision and Image Understanding, 2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Floating search methods in feature selectionPattern Recognition Letters, 1994