# Recent Advances in Zero-shot Recognition

arXiv: https://arxiv.org/abs/1710.04837 · HTML: https://mlsanity.com/paper/1710.04837/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2017.

## Built on by (most cited first, 28 of 28)

- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [Semantic Prompt for Few-Shot Image Recognition](https://mlsanity.com/paper/2303.14123/) (2023)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality](https://mlsanity.com/paper/2410.05210/) (2024)
- [Contributions of Shape, Texture, and Color in Visual Recognition](https://mlsanity.com/paper/2207.09510/) (2022)
- [An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2102.04016/) (2021)
- [Conterfactual Generative Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.06360/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval](https://mlsanity.com/paper/2104.09918/) (2021)
- [Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems](https://mlsanity.com/paper/2108.13592/) (2021)
- [Vocabulary-informed Zero-shot and Open-set Learning](https://mlsanity.com/paper/2301.00998/) (2023)
- [Zero-Shot Audio Classification using Image Embeddings](https://mlsanity.com/paper/2206.04984/) (2022)
- [How to Do Machine Learning with Small Data? -- A Review from an Industrial Perspective](https://mlsanity.com/paper/2311.07126/) (2023)
- [Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection](https://mlsanity.com/paper/2410.09908/) (2024)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)
- [Incrementally Zero-Shot Detection by an Extreme Value Analyzer](https://mlsanity.com/paper/2103.12609/) (2021)
- [CorrEmbed: Evaluating Pre-trained Model Image Similarity Efficacy with a Novel Metric](https://mlsanity.com/paper/2308.16126/) (2023)
- [Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification](https://mlsanity.com/paper/2102.13322/) (2021)
- [Recursive Training for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2103.00086/) (2021)
- [Latent Cognizance: What Machine Really Learns](https://mlsanity.com/paper/2110.15548/) (2021)
- [A Systematic Evaluation and Benchmark for Embedding-Aware Generative Models: Features, Models, and Any-shot Scenarios](https://mlsanity.com/paper/2302.04060/) (2023)
- [Indeterminate Probability Theory](https://mlsanity.com/paper/2303.11536/) (2023)

## Abstract (arXiv)

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem. One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings. We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. Importantly, we highlight the limitations of existing approaches and point out future research directions in this existing new research area.