# Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning

arXiv: https://arxiv.org/abs/2504.09990 · HTML: https://mlsanity.com/paper/2504.09990/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 39 of its 62 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 30 of 39)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Weakly-Supervised Semantic Segmentation via Sub-category Exploration](https://mlsanity.com/paper/2008.01183/) (2020)
- [On the Effectiveness of Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2211.15583/) (2022)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [A Unified Continual Learning Framework with General Parameter-Efficient Tuning](https://mlsanity.com/paper/2303.10070/) (2023)
- [Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition](https://mlsanity.com/paper/1908.07325/) (2019)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022)
- [LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs](https://mlsanity.com/paper/2401.16160/) (2024)
- [Multi-label Image Recognition by Recurrently Discovering Attentional Regions](https://mlsanity.com/paper/1711.02816/) (2017)
- [Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition](https://mlsanity.com/paper/2012.02994/) (2020)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning](https://mlsanity.com/paper/2307.13770/) (2023)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Improving Visual Prompt Tuning for Self-supervised Vision Transformers](https://mlsanity.com/paper/2306.05067/) (2023)
- [Revisiting the Power of Prompt for Visual Tuning](https://mlsanity.com/paper/2402.02382/) (2024)

## Built on by (most cited first, 4 of 4)

- [Fully Automated SAM for Single-source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2507.17281/) (2025)
- [[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)
- [Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2608.25653/) (2026)

## Abstract (arXiv)

Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence relationships among labels, which can lead to overfitting risk on this overemphasis, resulting in suboptimal models. To tackle this problem, we advocate for balancing correlative and discriminative relationships among labels to mitigate the risk of overfitting and enhance model performance. To this end, we propose the Multi-Label Visual Prompt Tuning framework, a novel and parameter-efficient method that groups classes into multiple class subsets according to label co-occurrence and mutual exclusivity relationships, and then models them respectively to balance the two relationships. In this work, since each group contains multiple classes, multiple prompt tokens are adopted within Vision Transformer (ViT) to capture the correlation or discriminative label relationship within each group, and effectively learn correlation or discriminative representations for class subsets. On the other hand, each group contains multiple group-aware visual representations that may correspond to multiple classes, and the mixture of experts (MoE) model can cleverly assign them from the group-aware to the label-aware, adaptively obtaining label-aware representation, which is more conducive to classification. Experiments on multiple benchmark datasets show that our proposed approach achieves competitive results and outperforms SOTA methods on multiple pre-trained models.