Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

intermediate attribute classifiers

Intermediate attribute classifiers are machine learning models trained to detect and score individual semantic or visual properties of an input, such as color, texture, or anatomical parts, rather than directly predicting high-level object categories. In paradigms such as zero-shot learning, these models serve as a mid-level semantic representation layer that bridges raw low-level features with final class labels. During training, individual classifiers learn to predict specific shared attributes across available labeled data. At inference, their combined attribute predictions are matched against predefined attribute profiles or signatures of candidate categories, enabling the identification of novel or unseen classes without requiring direct training examples for those specific target classes.

1 item

Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly

Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly

Yongqin Xian, Christoph H. Lampert, Bernt Schiele, Zeynep Akata

OrganizationsInstitute of Science and Technology AustriaMax Planck Institute for InformaticsUniversity of Amsterdam

Why you should read this

Establishes a unified evaluation benchmark and standardized data splits to resolve widespread test-set overlap in zero-shot learning, while introducing the Animals with Attributes 2 (AWA2) dataset and systematically comparing leading methods under both standard and generalized settings.

Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits of publicly available datasets used for this task. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss in detail the limitations of the current status of the area which can be taken as a basis for advancing it.

Added

2026-09-18