mlsanityData to 7 Oct 2026

Field-Guide-Inspired Zero-Shot Learning

arXiv 2108.10967 ↗First posted 24 Aug 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set of attributes for a novel category. Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment. This is especially the case when the recognition domain is an expert domain. We introduce a new field-guide-inspired approach to zero-shot annotation where the learner model interactively asks for the most useful attributes that define a class. We evaluate our method on classification benchmarks with attribute annotations like CUB, SUN, and AWA2 and show that our model achieves the performance of a model with full annotations at the cost of a significantly fewer number of annotations. Since the time of experts is precious, decreasing annotation cost can be very valuable for real-world deployment.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 24 Aug 2021.

Builds on

23 of 45 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  4. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  5. 2019Variational Adversarial Active Learningcited by 284
  6. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  7. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  8. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  9. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  10. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  11. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  12. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
11 more
  1. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  2. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  3. 2015Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptionscited by 64
  4. 2020State-Relabeling Adversarial Active Learningcited by 60
  5. 2016Less is more: zero-shot learning from online textual documents with noise suppressioncited by 40
  6. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  7. 2017Learning by Asking Questionscited by 25
  8. 2016Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learningcited by 20
  9. 2017Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categoriescited by 10
  10. 2017Improving One-Shot Learning through Fusing Side Informationcited by 10
  11. 2019Thinking Outside the Pool: Active Training Image Creation for Relative Attributescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2022On Guiding Visual Attention with Language Specificationcited by 30
  2. 2022VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learningcited by 27
  3. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  4. 2026Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensingcited by 0