# Creativity Inspired Zero-Shot Learning

arXiv: https://arxiv.org/abs/1904.01109 · HTML: https://mlsanity.com/paper/1904.01109/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2019.

## Built on by (most cited first, 27 of 27)

- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [Opening up Open-World Tracking](https://mlsanity.com/paper/2104.11221/) (2021)
- [NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research](https://mlsanity.com/paper/2211.11747/) (2022)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [CIZSL++: Creativity Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2101.00173/) (2021)
- [pOps: Photo-Inspired Diffusion Operators](https://mlsanity.com/paper/2406.01300/) (2024)
- [Piece it Together: Part-Based Concepting with IP-Priors](https://mlsanity.com/paper/2503.10365/) (2025)
- [Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization](https://mlsanity.com/paper/2101.09892/) (2021)
- [On Implicit Attribute Localization for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.04704/) (2021)
- [Domain-Aware Continual Zero-Shot Learning](https://mlsanity.com/paper/2112.12989/) (2021)
- [Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2402.02094/) (2024)
- [Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation](https://mlsanity.com/paper/2104.09757/) (2021)
- [Zero-shot Learning with Class Description Regularization](https://mlsanity.com/paper/2106.16108/) (2021)
- [MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning](https://mlsanity.com/paper/2203.01482/) (2022)
- [Continual Zero-Shot Learning through Semantically Guided Generative Random Walks](https://mlsanity.com/paper/2308.12366/) (2023)
- [MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2503.06847/) (2025)
- [Text2Model: Text-based Model Induction for Zero-shot Image Classification](https://mlsanity.com/paper/2210.15182/) (2022)
- [Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration](https://mlsanity.com/paper/2602.08615/) (2026)
- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [End-to-end Generative Zero-shot Learning via Few-shot Learning](https://mlsanity.com/paper/2102.04379/) (2021)
- [Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning](https://mlsanity.com/paper/2102.11566/) (2021)
- [Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification](https://mlsanity.com/paper/2102.13322/) (2021)
- [A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings](https://mlsanity.com/paper/2103.15939/) (2021)
- [Graceful Degradation and Related Fields](https://mlsanity.com/paper/2106.11119/) (2021)
- [Stylized Projected GAN: A Novel Architecture for Fast and Realistic Image Generation](https://mlsanity.com/paper/2307.16275/) (2023)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories with inspiration from the psychology of human creativity for producing novel art. We relate ZSL to human creativity by observing that zero-shot learning is about recognizing the unseen and creativity is about creating a likable unseen. We introduce a learning signal inspired by creativity literature that explores the unseen space with hallucinated class-descriptions and encourages careful deviation of their visual feature generations from seen classes while allowing knowledge transfer from seen to unseen classes. Empirically, we show consistent improvement over the state of the art of several percents on the largest available benchmarks on the challenging task or generalized ZSL from a noisy text that we focus on, using the CUB and NABirds datasets. We also show the advantage of our approach on Attribute-based ZSL on three additional datasets (AwA2, aPY, and SUN). Code is available.