Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
This work addresses a specific bottleneck in vision-language models for researchers and practitioners in computer vision, offering an incremental improvement in zero-shot classification accuracy.
The paper tackles the problem of ambiguous class descriptions in zero-shot image classification by proposing Follow-up Differential Descriptions (FuDD), which uses a Large Language Model to generate tailored descriptions that resolve ambiguities, resulting in consistent performance improvements over generic methods across 12 datasets and achieving comparable results to few-shot adaptation.
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.