# ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning

arXiv: https://arxiv.org/abs/2602.12401 · HTML: https://mlsanity.com/paper/2602.12401/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 63 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [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)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models](https://mlsanity.com/paper/2304.12526/) (2023)
- [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)
- [A Broad Study on the Transferability of Visual Representations with Contrastive Learning](https://mlsanity.com/paper/2103.13517/) (2021)
- [Zero-Shot Learning via Semantic Similarity Embedding](https://mlsanity.com/paper/1509.04767/) (2015)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2303.15322/) (2023)

## Abstract (arXiv)

Zero-shot Learning (ZSL) enables classifiers to recognize classes unseen during training, commonly via generative two stage methods: (1) learn visual semantic correlations from seen classes; (2) synthesize unseen class features from semantics to train classifiers. In this paper, we identify spurious visual semantic correlations in existing generative ZSL worsened by scarce seen class samples and introduce two metrics to quantify spuriousness for seen and unseen classes. Furthermore, we point out a more critical bottleneck: existing unadaptive fully noised generators produce features disconnected from real test samples, which also leads to the spurious correlation. To enhance the visual-semantic correlations on both seen and unseen classes, we propose ZeroDiff++, a diffusion-based generative framework. In training, ZeroDiff++ uses (i) diffusion augmentation to produce diverse noised samples, (ii) supervised contrastive (SC) representations for instance level semantics, and (iii) multi view discriminators with Wasserstein mutual learning to assess generated features. At generation time, we introduce (iv) Diffusion-based Test time Adaptation (DiffTTA) to adapt the generator using pseudo label reconstruction, and (v) Diffusion-based Test time Generation (DiffGen) to trace the diffusion denoising path and produce partially synthesized features that connect real and generated data, and mitigates data scarcity further. Extensive experiments on three ZSL benchmarks demonstrate that ZeroDiff++ not only achieves significant improvements over existing ZSL methods but also maintains robust performance even with scarce training data. Code would be available.