Few-Shot Adaptation for Multimedia Semantic Indexing

07/19/2018
by   Nakamasa Inoue, et al.
0

We propose a few-shot adaptation framework, which bridges zero-shot learning and supervised many-shot learning, for semantic indexing of image and video data. Few-shot adaptation provides robust parameter estimation with few training examples, by optimizing the parameters of zero-shot learning and supervised many-shot learning simultaneously. In this method, first we build a zero-shot detector, and then update it by using the few examples. Our experiments show the effectiveness of the proposed framework on three datasets: TRECVID Semantic Indexing 2010, 2014, and ImageNET. On the ImageNET dataset, we show that our method outperforms recent few-shot learning methods. On the TRECVID 2014 dataset, we achieve 15.19 under the zero-shot condition and the supervised condition, respectively. To the best of our knowledge, these are the best results on this dataset.

READ FULL TEXT
research
05/26/2016

Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

Leveraging class semantic descriptions and examples of known objects, ze...
research
10/22/2020

Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

Zero-shot classification is a generalization task where no instance from...
research
01/16/2020

Cluster-based Zero-shot learning for multivariate data

Supervised learning requires a sufficient training dataset which include...
research
04/17/2022

Learning Compositional Representations for Effective Low-Shot Generalization

We propose Recognition as Part Composition (RPC), an image encoding appr...
research
11/25/2019

Fast and Generalized Adaptation for Few-Shot Learning

The ability of fast generalizing to novel tasks from a few examples is c...
research
06/12/2018

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

It is one typical and general topic of learning a good embedding model t...
research
01/25/2019

Learning for New Visual Environments with Limited Labels

In computer vision applications, such as domain adaptation (DA), few sho...

Please sign up or login with your details

Forgot password? Click here to reset