Browsing by Author "Dr. Shafin Rahman"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    Few-Shot Learning - Learning from A Few Examples
    (North South University, 2022-12-30) K. M. Lutfor Rahman Student; Rahima Khatunn; Dr. Shafin Rahman; 1411162042; 1812062042
    Classifying visual objects have been a challenge for machines for quite some time. In the past we only depended on traditional machine learning approaches, but now there are lots of deep learning methods and approaches in order to do that. Researchers are still looking for a classification problem solution that requires very few resources, as training a classifier can be quite costly. So, Few-shot learning comes here to solve the problem. Few-shot learning is also known as FSL in short, is a method of identifying unseen/unknown classes (novel classes) with the help of very few examples or references. Although a huge amount of data is needed to train or teach a machine traditionally, it is not required for FSL. It can solve many real-world problems that are not possible using the typical machine learning approaches. Like humans, FSL models can learn by itself to classify visual objects. It uses the knowledge of already known classes to identify the new or unknown class. Also, it can reduce data collection/labeling costs as one of the most problematic step towards a good machine learning project is to collect properly labelled data. Here we’ll be working on an algorithm to implement a framework where a resulting classifier will be able to compare and identify previously unseen new classes from a few examples. After meta-training the model will be able to classify the classes comparing the relation between already learned information and input image. The relation will be defined by scalar scores, and the class that gets maximum score will get chosen. This relation-pair method improves the overall performance of FSL.
  • Thumbnail Image
    Item
    Restricted
    Fine-Grained Generalized Zero-Shot Learning
    (North South University, 2022-01-02) Sumaia Rahman Twinkle; Mohibul hasan Tarek; Anondo Hossain Rafi; Mahmudur Rahman Ifat; Dr. Shafin Rahman; ; 1430058042; 1813218042; 1813264042; 1912175642
    Fine-Grained Generalized Zero-Shot learning is the state of the art technology in the domain of computer vision and pattern recognition. In this project we are prepare our model to do GZSL where during the testing time an unseen/novel image will put as an in put to the model which image classes aren’t using during the training time. To overcomethisChallengeweleveragethesemanticinformationofthebothseen(source) and unseen(Target)classes to bridge the gap within them. To solve the fine-grained GZSL recognition of visually similar classes. To find out the difference between small intra-class and large intra-class variation, we use the dense attribute attention mechanism where for each attribute focus es on the most relevant image regions, obtaining attributes features. For classification training, we compute the score so attributes vector and classify the image attributes whose similarities is maximum with these mantic vector class. We conduct the experiment on the two popular data sets of CUB and AWA2 to examine our model.