Recognition of Unseen Bird Species by Learning from Field Guides
Not on the map. Why?
Abstract (arXiv)
We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species. We study two approaches: (1) a contrastive encoding of illustrations, which can be fed into standard 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 for zero-shot learning. On a subset of the iNaturalist2021 dataset with 749 seen and 739 unseen species, we obtain a classification accuracy of unseen bird species of 12% @top-1 and 38% @top-10, which shows the potential of field guides for challenging real-world scenarios with many species. Our code is available at https://github.com/ac-rodriguez/zslbillow
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 3 Jun 2022.
Builds on
33 of 55 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Neural Discrete Representation Learningcited by 4,650
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2020Supervised Contrastive Learningcited by 2,803
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
- 2015Return of Frustratingly Easy Domain Adaptationcited by 389
21 more
- 2018Understanding disentangling in β-VAEcited by 332
- 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
- 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
- 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 167
- 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
- 2015Label-Embedding for Image Classificationcited by 164
- 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
- 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
- 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
- 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
- 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
- 2020Invertible Zero-Shot Recognition Flowscited by 48
- 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
- 2018Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challengecited by 44
- 2019Deep Learning on Small Datasets without Pre-Training using Cosine Losscited by 41
- 2020Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labelscited by 24
- 2021Fine-Grained Zero-Shot Learning with DNA as Side Informationcited by 20
Built on by
Not cited yet.