# Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier

arXiv: https://arxiv.org/abs/2410.22317 · HTML: https://mlsanity.com/paper/2410.22317/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [Cones: Concept Neurons in Diffusion Models for Customized Generation](https://mlsanity.com/paper/2303.05125/) (2023)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing](https://mlsanity.com/paper/2309.15664/) (2023)
- [StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing](https://mlsanity.com/paper/2303.15649/) (2023)
- [PLOT: Prompt Learning with Optimal Transport for Vision-Language Models](https://mlsanity.com/paper/2210.01253/) (2022)
- [Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion](https://mlsanity.com/paper/2303.08767/) (2023)

## Built on by (most cited first, 10 of 10)

- [Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models](https://mlsanity.com/paper/2503.09864/) (2025)
- [One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models](https://mlsanity.com/paper/2505.21960/) (2025)
- [Adversarial Concept Distillation for One-Step Diffusion Personalization](https://mlsanity.com/paper/2510.20512/) (2025)
- [Forget Less by Learning Together through Concept Consolidation](https://mlsanity.com/paper/2601.01963/) (2026)
- [NumColor: Precise Numeric Color Control in Text-to-Image Generation](https://mlsanity.com/paper/2603.13547/) (2026)
- [MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation](https://mlsanity.com/paper/2605.12134/) (2026)
- [Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives](https://mlsanity.com/paper/2607.26735/) (2026)
- [Few-shot multi-token DreamBooth with LoRa for style-consistent character generation](https://mlsanity.com/paper/2510.09475/) (2025)
- [Forget Less by Learning from Parents Through Hierarchical Relationships](https://mlsanity.com/paper/2601.01892/) (2026)
- [LiteEmbed: Adapting CLIP to Rare Classes](https://mlsanity.com/paper/2601.09661/) (2026)

## Abstract (arXiv)

With the advent of large pre-trained vision-language models such as CLIP, prompt learning methods aim to enhance the transferability of the CLIP model. They learn the prompt given few samples from the downstream task given the specific class names as prior knowledge, which we term as semantic-aware classification. However, in many realistic scenarios, we only have access to few samples and knowledge of the class names (e.g., when considering instances of classes). This challenging scenario represents the semantic-agnostic discriminative case. Text-to-Image (T2I) personalization methods aim to adapt T2I models to unseen concepts by learning new tokens and endowing these tokens with the capability of generating the learned concepts. These methods do not require knowledge of class names as a semantic-aware prior. Therefore, in this paper, we first explore Textual Inversion and reveal that the new concept tokens possess both generation and classification capabilities by regarding each category as a single concept. However, learning classifiers from single-concept textual inversion is limited since the learned tokens are suboptimal for the discriminative tasks. To mitigate this issue, we propose Multi-Class textual inversion, which includes a discriminative regularization term for the token updating process. Using this technique, our method MC-TI achieves stronger Semantic-Agnostic Classification while preserving the generation capability of these modifier tokens given only few samples per category. In the experiments, we extensively evaluate MC-TI on 12 datasets covering various scenarios, which demonstrates that MC-TI achieves superior results in terms of both classification and generation outcomes.