# Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

arXiv: https://arxiv.org/abs/1909.05995 · HTML: https://mlsanity.com/paper/1909.05995/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2019.

## Built on by (most cited first, 30 of 42)

- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)
- [Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization](https://mlsanity.com/paper/2308.03950/) (2023)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Zero-Shot Compositional Concept Learning](https://mlsanity.com/paper/2107.05176/) (2021)
- [Image-free Classifier Injection for Zero-Shot Classification](https://mlsanity.com/paper/2308.10599/) (2023)
- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [Zero-Shot Logit Adjustment](https://mlsanity.com/paper/2204.11822/) (2022)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2406.00639/) (2024)
- [Deconstructed Generation-Based Zero-Shot Model](https://mlsanity.com/paper/2204.11280/) (2022)
- [A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture](https://mlsanity.com/paper/2210.11318/) (2022)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Evolutionary Generalized Zero-Shot Learning](https://mlsanity.com/paper/2211.13174/) (2022)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [Visual-Semantic Graph Matching Net for Zero-Shot Learning](https://mlsanity.com/paper/2411.11351/) (2024)
- [Explaining CLIP Zero-shot Predictions Through Concepts](https://mlsanity.com/paper/2603.28211/) (2026)
- [Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning](https://mlsanity.com/paper/2102.11856/) (2021)
- [Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition](https://mlsanity.com/paper/2105.15093/) (2021)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Bias-Eliminated Semantic Refinement for Any-Shot Learning](https://mlsanity.com/paper/2202.04827/) (2022)
- [Interpretable Saliency Maps And Self-Supervised Learning For Generalized Zero Shot Medical Image Classification](https://mlsanity.com/paper/2204.01728/) (2022)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from one feature space to the other. Despite being reasonable, previous approaches essentially discard the highly precious discriminative power of visual features in an implicit way, and thus produce undesirable results. We instead reformulate ZSL as a conditioned visual classification problem, i.e., classifying visual features based on the classifiers learned from the semantic descriptions. With this reformulation, we develop algorithms targeting various ZSL settings: For the conventional setting, we propose to train a deep neural network that directly generates visual feature classifiers from the semantic attributes with an episode-based training scheme; For the generalized setting, we concatenate the learned highly discriminative classifiers for seen classes and the generated classifiers for unseen classes to classify visual features of all classes; For the transductive setting, we exploit unlabeled data to effectively calibrate the classifier generator using a novel learning-without-forgetting self-training mechanism and guide the process by a robust generalized cross-entropy loss. Extensive experiments show that our proposed algorithms significantly outperform state-of-the-art methods by large margins on most benchmark datasets in all the ZSL settings. Our code is available at urlhttps://github.com/kailigo/cvcZSL