Zero-Shot Bird Species Recognition by Learning from Field Guides

06/03/2022
by   Andres C Rodriguez, et al.
0

We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. The illustrations contained in field guides deliberately focus on discriminative properties of a species, and can serve as side information to transfer knowledge from seen to unseen classes. We study two approaches: (1) a contrastive encoding of illustrations that can be fed into zero-shot learning schemes; and (2) a novel method that leverages the fact that illustrations are also images and as such structurally more similar to photographs than other kinds of side information. Our results show that illustrations from field guides, which are readily available for a wide range of species, are indeed a competitive source of side information. On the iNaturalist2021 subset, we obtain a harmonic mean from 749 seen and 739 unseen classes greater than 45% (@top-10) and 15% (@top-1). Which shows that field guides are a valuable option for challenging real-world scenarios with many species.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2020

ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

We study the problem of recognizing visual entities from the textual des...
research
08/16/2019

Transferable Contrastive Network for Generalized Zero-Shot Learning

Zero-shot learning (ZSL) is a challenging problem that aims to recognize...
research
09/29/2021

Fine-Grained Zero-Shot Learning with DNA as Side Information

Fine-grained zero-shot learning task requires some form of side-informat...
research
10/11/2020

Complexity-based speciation and genotype representation for neuroevolution

This paper introduces a speciation principle for neuroevolution where ev...
research
09/15/2023

Exploring Meta Information for Audio-based Zero-shot Bird Classification

Advances in passive acoustic monitoring and machine learning have led to...
research
12/12/2021

Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species

Current non-rigid object keypoint detectors perform well on a chosen kin...
research
11/21/2018

Recent Advances in Open Set Recognition: A Survey

In real-world recognition/classification tasks, limited by various objec...

Please sign up or login with your details

Forgot password? Click here to reset