# SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning

arXiv: https://arxiv.org/abs/2503.10252 · HTML: https://mlsanity.com/paper/2503.10252/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 78 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [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)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [The Devil in Linear Transformer](https://mlsanity.com/paper/2210.10340/) (2022)
- [A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts](https://mlsanity.com/paper/1712.01381/) (2017)
- [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)
- [Episode-based Prototype Generating Network for Zero-Shot Learning](https://mlsanity.com/paper/1909.03360/) (2019)
- [Semantic-Guided Multi-Attention Localization for Zero-Shot Learning](https://mlsanity.com/paper/1903.00502/) (2019)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [Semantics Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.07978/) (2021)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Invertible Zero-Shot Recognition Flows](https://mlsanity.com/paper/2007.04873/) (2020)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition](https://mlsanity.com/paper/2006.08939/) (2020)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion](https://mlsanity.com/paper/2004.14795/) (2020)
- [Domain Adaptive Semantic Segmentation without Source Data](https://mlsanity.com/paper/2110.06484/) (2021)

## Built on by (most cited first, 6 of 6)

- [Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization](https://mlsanity.com/paper/2507.15504/) (2025)
- [Distributed Zero-Shot Learning for Visual Recognition](https://mlsanity.com/paper/2511.08170/) (2025)
- [Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction](https://mlsanity.com/paper/2606.24156/) (2026)
- [Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2606.24165/) (2026)
- [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations](https://mlsanity.com/paper/2512.12219/) (2025)
- [PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learning](https://mlsanity.com/paper/2601.14111/) (2026)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims to recognize unseen classes without labeled training examples by leveraging class-level semantic descriptors such as attributes. A fundamental challenge in ZSL is semantic misalignment, where semantic-unrelated information involved in visual features introduce ambiguity to visual-semantic interaction. Unlike existing methods that suppress semantic-unrelated information post hoc either in the feature space or the model space, we propose addressing this issue at the input stage, preventing semantic-unrelated patches from propagating through the network. To this end, we introduce Semantically contextualized VIsual Patches (SVIP) for ZSL, a transformer-based framework designed to enhance visual-semantic alignment. Specifically, we propose a self-supervised patch selection mechanism that preemptively learns to identify semantic-unrelated patches in the input space. This is trained with the supervision from aggregated attention scores across all transformer layers, which estimate each patch's semantic score. As removing semantic-unrelated patches from the input sequence may disrupt object structure, we replace them with learnable patch embeddings. With initialization from word embeddings, we can ensure they remain semantically meaningful throughout feature extraction. Extensive experiments on ZSL benchmarks demonstrate that SVIP achieves state-of-the-art performance results while providing more interpretable and semantically rich feature representations. Code is available at https://github.com/uqzhichen/SVIP.