Few Shots Text To Image Retrieval: New Benchmarking Dataset And Optimization Methods

Abstract

Pre-trained vision-language models (VLMs) excel in multimodal tasks, commonly encoding images as embedding vectors for storage in databases and retrieval via approximate nearest neighbor search (ANNS). However, these models struggle with compositional queries and out-of-distribution (OOD) image-text pairs. Inspired by human cognition's ability to learn from minimal examples, we address this performance gap through few-shot learning approaches specifically designed for image retrieval. We introduce the Few-Shot Text-to-Image Retrieval (FSIR) task and its accompanying benchmark dataset, FSIR-BD - the first to explicitly target image retrieval by text accompanied by reference examples, focusing on the challenging compositional and OOD queries. The compositional part is divided to urban scenes and nature species, both in specific situations or with distinctive features. FSIR-BD contains 38,353 images and 303 queries, with 82% comprising the test corpus (averaging per query 37 positives, gr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyidan2026few

Related papers

• EFSA: Episodic Few-shot Adaptation For Text-to-image Retrieval (2024)0.00
• Advancing Image Retrieval With Few-shot Learning And Relevance Feedback (2023)0.00
• Rethinking Benchmarks For Cross-modal Image-text Retrieval (2023)13.11
• Few-shot Learning Through An Information Retrieval Lens (2017)0.00
• Few-shot Recognition Via Stage-wise Retrieval-augmented Finetuning (2024)4.52
• Zero Shot Composed Image Retrieval (2025)1.57
• Flickr30k-cfq: A Compact And Fragmented Query Dataset For Text-image Retrieval (2024)3.58
• Shotfinder: Imagination-driven Open-domain Video Shot Retrieval Via Web Search (2026)0.00