# Field-Guide-Inspired Zero-Shot Learning

arXiv: https://arxiv.org/abs/2108.10967 · HTML: https://mlsanity.com/paper/2108.10967/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 24 Aug 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Synthesized Classifiers for Zero-Shot Learning](https://mlsanity.com/paper/1603.00550/) (2016)
- [A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts](https://mlsanity.com/paper/1712.01381/) (2017)
- [Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions](https://mlsanity.com/paper/1506.00511/) (2015)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Less is more: zero-shot learning from online textual documents with noise suppression](https://mlsanity.com/paper/1604.01146/) (2016)
- [A Simple Exponential Family Framework for Zero-Shot Learning](https://mlsanity.com/paper/1707.08040/) (2017)
- [Learning by Asking Questions](https://mlsanity.com/paper/1712.01238/) (2017)
- [Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning](https://mlsanity.com/paper/1610.04787/) (2016)
- [Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categories](https://mlsanity.com/paper/1704.03607/) (2017)
- [Improving One-Shot Learning through Fusing Side Information](https://mlsanity.com/paper/1710.08347/) (2017)
- [Thinking Outside the Pool: Active Training Image Creation for Relative Attributes](https://mlsanity.com/paper/1901.02551/) (2019)

## Built on by (most cited first, 4 of 4)

- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2203.10444/) (2022)
- [Instance-level Few-shot Learning with Class Hierarchy Mining](https://mlsanity.com/paper/2304.07459/) (2023)
- [Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing](https://mlsanity.com/paper/2609.38603/) (2026)

## 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.