Vocabulary-informed Extreme Value Learning

05/28/2017
by   Yanwei Fu, et al.
0

The novel unseen classes can be formulated as the extreme values of known classes. This inspired the recent works on open-set recognition Scheirer_2013_TPAMI,Scheirer_2014_TPAMIb,EVM, which however can have no way of naming the novel unseen classes. To solve this problem, we propose the Extreme Value Learning (EVL) formulation to learn the mapping from visual feature to semantic space. To model the margin and coverage distributions of each class, the Vocabulary-informed Learning (ViL) is adopted by using vast open vocabulary in the semantic space. Essentially, by incorporating the EVL and ViL, we for the first time propose a novel semantic embedding paradigm -- Vocabulary-informed Extreme Value Learning (ViEVL), which embeds the visual features into semantic space in a probabilistic way. The learned embedding can be directly used to solve supervised learning, zero-shot and open set recognition simultaneously. Experiments on two benchmark datasets demonstrate the effectiveness of proposed frameworks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/24/2016

Semi-supervised Vocabulary-informed Learning

Despite significant progress in object categorization, in recent years, ...
07/07/2016

Zero-Shot Visual Recognition via Bidirectional Latent Embedding

Zero-shot learning for visual recognition, e.g., object and action recog...
03/15/2017

Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths

Zero-shot recognition aims to accurately recognize objects of unseen cla...
05/04/2017

From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis

Robust object recognition systems usually rely on powerful feature extra...
08/04/2020

Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

We propose a novel algorithm, named Open-Edit, which is the first attemp...
08/29/2020

Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature

Recently, many zero-shot learning (ZSL) methods focused on learning disc...
12/22/2021

Open-Vocabulary Image Segmentation

We design an open-vocabulary image segmentation model to organize an ima...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.