Graph-based deep models for image semantic segmentation

Image segmentation is a fundamental task in computer vision, classifying each pixel in a image into categories is important to many real world applications. However, acquiring ground truth labels to train deep visual models have been labour-intensive and costly. Recent works have emerged to reduce t...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Peh, Wei Hang
مؤلفون آخرون: Ke Yiping, Kelly
التنسيق: Final Year Project
اللغة:English
منشور في: Nanyang Technological University 2024
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/10356/175317
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
المؤسسة: Nanyang Technological University
اللغة: English
الوصف
الملخص:Image segmentation is a fundamental task in computer vision, classifying each pixel in a image into categories is important to many real world applications. However, acquiring ground truth labels to train deep visual models have been labour-intensive and costly. Recent works have emerged to reduce the cost in training segmentation models using semi-supervised, weakly-supervised, and unsupervised methods. In this study, we use deep features extracted using Vision Transformers and cluster these features using Graph Attention Networks with optimisation objectives from classical graph theory. We apply this proposed method for unsupervised object segmentation and our model yields good performance on the DUTS and ESCCD datasets.