# Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

arXiv: https://arxiv.org/abs/2311.07593 · HTML: https://mlsanity.com/paper/2311.07593/

## Key facts

- Cited by 13 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 44 of its 55 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## 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 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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)

## Built on by (most cited first, 13 of 13)

- [Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis](https://mlsanity.com/paper/2511.22033/) (2025)
- [Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning](https://mlsanity.com/paper/2410.03321/) (2024)
- [If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions](https://mlsanity.com/paper/2403.16442/) (2024)
- [PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck](https://mlsanity.com/paper/2403.05297/) (2024)
- [Finetuning CLIP to Reason about Pairwise Differences](https://mlsanity.com/paper/2409.09721/) (2024)
- [Does VLM Classification Benefit from LLM Description Semantics?](https://mlsanity.com/paper/2412.11917/) (2024)
- [Interactive Data Harmonization with LLM Agents: Opportunities and Challenges](https://mlsanity.com/paper/2502.07132/) (2025)
- [DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition](https://mlsanity.com/paper/2502.00618/) (2025)
- [SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models](https://mlsanity.com/paper/2502.16911/) (2025)
- [DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition](https://mlsanity.com/paper/2511.18305/) (2025)
- [CoAPT: Context Attribute words for Prompt Tuning](https://mlsanity.com/paper/2407.13808/) (2024)
- [Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark](https://mlsanity.com/paper/2503.10357/) (2025)
- [Retrieval Enhanced Feedback via In-context Neural Error-book](https://mlsanity.com/paper/2508.16313/) (2025)

## Abstract (arXiv)

A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.