Saved in:
Bibliographic Details
Main Authors: Amosy, Ohad, Volk, Tomer, Shapira, Eilam, Ben-David, Eyal, Reichart, Roi, Chechik, Gal
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.15182
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914960322330624
author Amosy, Ohad
Volk, Tomer
Shapira, Eilam
Ben-David, Eyal
Reichart, Roi
Chechik, Gal
author_facet Amosy, Ohad
Volk, Tomer
Shapira, Eilam
Ben-David, Eyal
Reichart, Roi
Chechik, Gal
contents We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that learn a fixed representation of the output classes, we generate at inference time a model tailored to a query classification task. To generate task-based zero-shot classifiers, we train a hypernetwork that receives class descriptions and outputs a multi-class model. The hypernetwork is designed to be equivariant with respect to the set of descriptions and the classification layer, thus obeying the symmetries of the problem and improving generalization. Our approach generates non-linear classifiers, handles rich textual descriptions, and may be adapted to produce lightweight models efficient enough for on-device applications. We evaluate this approach in a series of zero-shot classification tasks, for image, point-cloud, and action recognition, using a range of text descriptions: From single words to rich descriptions. Our results demonstrate strong improvements over previous approaches, showing that zero-shot learning can be applied with little training data. Furthermore, we conduct an analysis with foundational vision and language models, demonstrating that they struggle to generalize when describing what attributes the class lacks.
format Preprint
id arxiv_https___arxiv_org_abs_2210_15182
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Text2Model: Text-based Model Induction for Zero-shot Image Classification
Amosy, Ohad
Volk, Tomer
Shapira, Eilam
Ben-David, Eyal
Reichart, Roi
Chechik, Gal
Computer Vision and Pattern Recognition
Machine Learning
We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that learn a fixed representation of the output classes, we generate at inference time a model tailored to a query classification task. To generate task-based zero-shot classifiers, we train a hypernetwork that receives class descriptions and outputs a multi-class model. The hypernetwork is designed to be equivariant with respect to the set of descriptions and the classification layer, thus obeying the symmetries of the problem and improving generalization. Our approach generates non-linear classifiers, handles rich textual descriptions, and may be adapted to produce lightweight models efficient enough for on-device applications. We evaluate this approach in a series of zero-shot classification tasks, for image, point-cloud, and action recognition, using a range of text descriptions: From single words to rich descriptions. Our results demonstrate strong improvements over previous approaches, showing that zero-shot learning can be applied with little training data. Furthermore, we conduct an analysis with foundational vision and language models, demonstrating that they struggle to generalize when describing what attributes the class lacks.
title Text2Model: Text-based Model Induction for Zero-shot Image Classification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2210.15182