Low-shot Visual Recognition
Many real world datasets are characterized by having a long tailed distribution, with several samples for some classes and only a few samples for other classes. While many Deep Learning based solutions exist for object recognition when hundreds of samples are available, there are not many solutions...
Main Author: | Pemula, Latha |
---|---|
Other Authors: | Electrical and Computer Engineering |
Format: | Others |
Published: |
Virginia Tech
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/10919/73321 |
Similar Items
-
Zero-shot Learning for Visual Recognition Problems
by: Naha, Shujon
Published: (2016) -
Zero-Shot Visual Recognition via Semantic Attention-Based Compare Network
by: Fudong Nian, et al.
Published: (2020-01-01) -
Zero Shot Learning for Visual Object Recognition with Generative Models
Published: (2020) -
Zero-Shot Human Activity Recognition Using Non-Visual Sensors
by: Fadi Al Machot, et al.
Published: (2020-02-01) -
A Few-Shot Learning Method Using Feature Reparameterization and Dual-Distance Metric Learning for Object Re-Identification
by: Sheng-Hung Fan, et al.
Published: (2021-01-01)