# SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models

arXiv: https://arxiv.org/abs/2502.16911 · HTML: https://mlsanity.com/paper/2502.16911/

## Key facts

- Cited by 2 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 18 of its 25 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## 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, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2206.09541/) (2022)
- [Waffling around for Performance: Visual Classification with Random Words and Broad Concepts](https://mlsanity.com/paper/2306.07282/) (2023)
- [CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets](https://mlsanity.com/paper/2302.02551/) (2023)
- [Texts as Images in Prompt Tuning for Multi-Label Image Recognition](https://mlsanity.com/paper/2211.12739/) (2022)
- [CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2307.16634/) (2023)
- [DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2308.01890/) (2023)
- [TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training](https://mlsanity.com/paper/2312.12828/) (2023)
- [TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt](https://mlsanity.com/paper/2405.06926/) (2024)
- [Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification](https://mlsanity.com/paper/2311.07593/) (2023)
- [Text-Region Matching for Multi-Label Image Recognition with Missing Labels](https://mlsanity.com/paper/2407.18520/) (2024)
- [Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning](https://mlsanity.com/paper/2403.01209/) (2024)
- [Improving Multi-label Recognition using Class Co-Occurrence Probabilities](https://mlsanity.com/paper/2404.16193/) (2024)
- [Text as Image: Learning Transferable Adapter for Multi-Label Classification](https://mlsanity.com/paper/2312.04160/) (2023)
- [SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition](https://mlsanity.com/paper/2407.20920/) (2024)

## Built on by (most cited first, 2 of 2)

- [[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation](https://mlsanity.com/paper/2605.25821/) (2026)
- [FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models](https://mlsanity.com/paper/2605.28347/) (2026)

## Abstract (arXiv)

Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural adaptations, limiting zero-shot applicability. Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth. Using large language model insights on object co-occurrence, we introduce compound prompts grounded in realistic object combinations. Analysis of these prompt scores reveals VLM biases and ``AND''/``OR'' signal ambiguities, notably that maximum compound scores are surprisingly suboptimal compared to second-highest scores. We address these through a debiasing and score-fusion algorithm that corrects image bias and clarifies VLM response behaviors. Our method enhances other zero-shot approaches, consistently improving their results. Experiments show superior mean Average Precision (mAP) compared to methods requiring training data, achieved through refined object ranking for robust zero-shot MLR.