Zero Shot Recognition with Unreliable Attributes

TL;DR

This paper introduces a robust zero-shot learning method using random forests that explicitly models attribute prediction unreliability, improving recognition accuracy for unseen categories, especially in few-shot scenarios.

Contribution

It presents a novel random forest approach that accounts for attribute unreliability, enhancing zero-shot and few-shot recognition performance.

Findings

Improved zero-shot recognition accuracy on three datasets.

Effective handling of unreliable attribute predictions.

Enhanced performance in few-shot learning scenarios.

Abstract

In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can construct a classifier for the zebra category by enumerating which properties it possesses---even without providing zebra training images. In practice, however, the standard zero-shot paradigm suffers because attribute predictions in novel images are hard to get right. We propose a novel random forest approach to train zero-shot models that explicitly accounts for the unreliability of attribute predictions. By leveraging statistics about each attribute's error tendencies, our method obtains more robust discriminative models for the unseen classes. We further devise extensions to handle the few-shot scenario and unreliable attribute descriptions. On three datasets, we demonstrate the benefit for visual category learning with zero or few training examples, a critical domain for rare categories or categories defined on the fly.