Attribute Prototype Network for Zero-Shot Learning

By Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata. Neural Information Processing Systems, 2020

380 citations recorded by the source corpus.

From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with integrated attribute localization ability would be beneficial for zero-shot learning. To this end, we propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. We show that our locality augmented image representations achieve a new state-of-the-art on three zero-shot learning benchmarks. As an additional benefit, our model points to the visual evidence of the attributes in an image, e.g. for the CUB dataset, confirming the improved attribute localization ability of our image representation. The code will be publicaly available at this https URL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/91f602d5b271be8b76576d980bd387530b4eec44

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A Review of Generalized Zero-Shot Learning Methods (2020, methodology): “Later, several studies used the calibrated stacking technique to solve the GZSL problem [73], [78], [79], [80], [81].”
Rethinking Semantic Segmentation: A Prototype View (2022, background): “There has been a recent surge of interest to integrate deep learning into prototype learning, showing good potential in few-shot [98], zero-shot [54], and unsupervised learning [116, 120], as well as supervised classification [38, 83, 115, 123] and interpretable networks [65].”
Open-vocabulary Attribute Detection (2022, background): “Another line of work [1,42,47] focuses on zero-shot object classification by inferring the attributes of an object as an intermediate step or relying on object-attribute compositionality [1, 8, 28] for zero-shot attribute-object classification.”