# Vocabulary-informed Extreme Value Learning

arXiv: https://arxiv.org/abs/1705.09887 · HTML: https://mlsanity.com/paper/1705.09887/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2017.

## Built on by (most cited first, 1 of 1)

- [Egocentric Hierarchical Visual Semantics](https://mlsanity.com/paper/2305.05422/) (2023)

## Abstract (arXiv)

The novel unseen classes can be formulated as the extreme values of known classes. This inspired the recent works on open-set recognition citeScheirer2013TPAMI,Scheirer2014TPAMIb,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.