# Image-free Classifier Injection for Zero-Shot Classification

arXiv: https://arxiv.org/abs/2308.10599 · HTML: https://mlsanity.com/paper/2308.10599/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 70 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [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)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Rethinking Knowledge Graph Propagation for Zero-Shot Learning](https://mlsanity.com/paper/1805.11724/) (2018)

## Built on by (most cited first, 15 of 15)

- [Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2404.07713/) (2024)
- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance](https://mlsanity.com/paper/2511.00543/) (2025)
- [Learning to Learn Weight Generation via Local Consistency Diffusion](https://mlsanity.com/paper/2502.01117/) (2025)
- [Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2503.23030/) (2025)
- [Explaining CLIP Zero-shot Predictions Through Concepts](https://mlsanity.com/paper/2603.28211/) (2026)
- [ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning](https://mlsanity.com/paper/2408.14868/) (2024)
- [Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification](https://mlsanity.com/paper/2405.02155/) (2024)
- [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations](https://mlsanity.com/paper/2512.12219/) (2025)
- [Mutually Causal Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2603.17412/) (2026)
- [Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues](https://mlsanity.com/paper/2603.21138/) (2026)
- [Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling](https://mlsanity.com/paper/2605.22484/) (2026)
- [CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension](https://mlsanity.com/paper/2608.13751/) (2026)

## Abstract (arXiv)

Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from scratch with specialised methods: therefore, access to a training dataset is required when the need for zero-shot classification arises. In this paper, we aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data. Instead, the existing classifier weights and simple class-wise descriptors, such as class names or attributes, are used. ICIS has two encoder-decoder networks that learn to reconstruct classifier weights from descriptors (and vice versa), exploiting (cross-)reconstruction and cosine losses to regularise the decoding process. Notably, ICIS can be cheaply trained and applied directly on top of pre-trained classification models. Experiments on benchmark ZSL datasets show that ICIS produces unseen classifier weights that achieve strong (generalised) zero-shot classification performance. Code is available at https://github.com/ExplainableML/ImageFreeZSL .