Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning

• URL: http://arxiv.org/abs/2604.03657v1
• Date: Sat, 04 Apr 2026 09:18:31 GMT
• Title: Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
• Abstract summary: Visual in-context learning (VICL) enables visual foundation models to handle multiple tasks by steering them with demonstrative prompts.<n>The choice of such prompts largely influences VICL performance, standing out as a key challenge.<n>We develop a framework named LaPR (Label-aware Prompt Retrieval) which highlights the role of labels in prompt selection.
• Score: 79.61386774847357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual in-context learning (VICL) enables visual foundation models to handle multiple tasks by steering them with demonstrative prompts. The choice of such prompts largely influences VICL performance, standing out as a key challenge. Prior work has made substantial progress on prompt retrieval and reranking strategies, but mainly focuses on prompt images while overlooking labels. We reveal these approaches sometimes get visually similar but label-inconsistent prompts, which potentially degrade VICL performance. On the other hand, higher label consistency between query and prompts preferably indicates stronger VICL results. Motivated by these findings, we develop a framework named LaPR (Label-aware Prompt Retrieval), which highlights the role of labels in prompt selection. Our framework first designs an image-label joint representation for prompts to incorporate label cues explicitly. Besides, to handle unavailable query labels at test time, we introduce a mixture-of-expert mechanism to the dual encoders with query-adaptive routing. Each expert is expected to capture a specific label mode, while the router infers query-adaptive mixture weights and helps to learn label-aware representation. We carefully design alternative optimization for experts and router, with a VICL performance-guided contrastive loss and a label-guided contrastive loss, respectively. Extensive experiments show promising and consistent improvement of LaPR on in-context segmentation, detection, and colorization tasks. Moreover, LaPR generalizes well across feature extractors and cross-fold scenarios, suggesting the importance of label utilization in prompt retrieval for VICL. Code is available at https://github.com/luotc-why/CVPR26-LaPR.

Related papers

• ConText: Driving In-context Learning for Text Removal and Segmentation [59.6299939669307]
  This paper presents the first study on adapting the visual in-context learning paradigm to optical character recognition tasks.<n>We propose a task-chaining compositor in the form of image-removal-segmentation.<n>We also introduce context-aware aggregation, integrating the chained prompt pattern into the latent query representation.
  arXiv  Detail & Related papers  (2025-06-04T10:06:32Z)
• Tuning Vision-Language Models with Candidate Labels by Prompt Alignment [8.944708621017812]
  Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs.<n> Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks.<n>We propose a framework to guide the learning process with candidate labels.
  arXiv  Detail & Related papers  (2024-07-10T13:19:31Z)
• PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition [47.11517266162346]
  We propose a Prompt-driven Visual-Linguistic Representation Learning framework to better leverage the capabilities of the linguistic modality. In contrast to the unidirectional fusion in previous works, we introduce a Dual-Modal Attention (DMA) that enables bidirectional interaction between textual and visual features.
  arXiv  Detail & Related papers  (2024-01-31T14:39:11Z)
• Leveraging Label Information for Multimodal Emotion Recognition [22.318092635089464]
  Multimodal emotion recognition (MER) aims to detect the emotional status of a given expression by combining the speech and text information. We propose a novel approach for MER by leveraging label information. We devise a novel label-guided attentive fusion module to fuse the label-aware text and speech representations for emotion classification.
  arXiv  Detail & Related papers  (2023-09-05T10:26:32Z)
• DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations [79.433122872973]
  Multi-label image recognition in the low-label regime is a task of great challenge and practical significance. We leverage the powerful alignment between textual and visual features pretrained with millions of auxiliary image-text pairs. We introduce an efficient and effective framework called Evidence-guided Dual Context Optimization (DualCoOp++)
  arXiv  Detail & Related papers  (2023-08-03T17:33:20Z)
• Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels [60.675714333081466]
  Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, ie, CLIP, to compensate for insufficient annotations. We advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior.
  arXiv  Detail & Related papers  (2023-03-23T12:39:20Z)
• Texts as Images in Prompt Tuning for Multi-Label Image Recognition [70.9310322461598]
  We advocate that image-text contrastive learning makes it feasible to treat texts as images for prompt tuning and introduce TaI prompting. Particularly, we apply TaI prompting to multi-label image recognition, where sentences in the wild serve as alternatives to images for prompt tuning. Our proposed TaI-DPT outperforms zero-shot CLIP by a large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-11-23T07:00:11Z)
• Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [75.44233392355711]
  KGGR framework exploits prior knowledge of statistical label correlations with deep neural networks. It first builds a structured knowledge graph to correlate different labels based on statistical label co-occurrence. Then, it introduces the label semantics to guide learning semantic-specific features. It exploits a graph propagation network to explore graph node interactions.
  arXiv  Detail & Related papers  (2020-09-20T15:05:29Z)
• Label-Wise Document Pre-Training for Multi-Label Text Classification [14.439051753832032]
  This paper develops Label-Wise Pre-Training (LW-PT) method to get a document representation with label-aware information. The basic idea is that, a multi-label document can be represented as a combination of multiple label-wise representations, and that, correlated labels always cooccur in the same or similar documents.
  arXiv  Detail & Related papers  (2020-08-15T10:34:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.