Many-Class Few-Shot Classification

Please enable javascript in your browser.

Fereydooni, Mohammad Reza | 2024

5 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 56914 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Soleymani Baghshah, Mahdieh
Abstract:
Few-shot learning methods have achieved notable performance in recent years. However, fewshot learning in large-scale settings with hundreds of classes is still challenging. In this dissertation, we tackle the problems of large-scale few-shot learning by taking advantage of pre-trained foundation models. We recast the original problem in two levels with different granularity. At the coarse-grained level, we introduce a novel object recognition approach with robustness to sub-population shifts. At the fine-grained level, generative experts are designed for few-shot learning, specialized for different superclasses. A Bayesian schema is considered to combine coarse-grained information with fine-grained predictions in a winnertakes-all fashion. Extensive experiments on large-scale datasets and different architectures show that the proposed method is both effective and efficient besides its simplicity and natural problem remodeling.
Keywords:
Deep Learning ; Few-Shot Learning ; Hierarchical Classification ; Generalization ; Robustness ; Bayesian Learning ; Large-Scale Classification