Skip to content
AI News HubLIVE
Original source2 min read

Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery

Summary

AptM-GCD introduces Attribute-Evidence Learning (AEL) and Multimodal Prompt Learning (MPL) to treat attributes as localized visual evidence, avoiding misleading global alignment and achieving state-of-the-art results on six datasets.

SourcearXiv Computer VisionAuthor: Wei Zhang, Zhu Teng, Zhixiang Chi, Junnan Zou, Wenxin Luo, Linfeng Ye, Jianping Fan, Konstantions N. Plataniotis
Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 8 Nov 2026]

Title:Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery

View a PDF of the paper titled Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery, by Wei Zhang and 7 other authors

View PDF HTML (experimental)

Abstract:Generalized category discovery (GCD) aims to discover novel categories from unlabeled data by leveraging limited labeled samples from old classes. Existing methods that rely solely on visual cues often neglect the multimodal nature of human perception, prompting recent approaches to incorporate textual information such as category tags and attributes. However, these approaches typically entangle global tags and local attributes within a shared global image representation, rendering attributes unreliable and potentially providing misleading cues that can drive the model toward incorrect predictions. To this end, we propose AptM-GCD, a novel multimodal framework that exploits apt textual guidance through attribute evidence learning and multimodal prompt reasoning. Specifically, we design an Attribute-Evidence Learning (AEL) mechanism that treats attributes as localized visual evidence rather than global category descriptors. By interacting attribute embeddings with patch-level visual tokens, AEL identifies reliable attribute-related regions and extracts discriminative local evidence, thereby reducing the impact of noisy or irrelevant attribute cues. Building upon the extracted evidence, we further develop a Multimodal Prompt Learning (MPL) mechanism to bridge local attribute semantics and global visual understanding. MPL converts fine-grained textual evidence into visual prompts and injects them into a multimodal prompt transformer, enabling attribute information to enhance category discrimination through contextual reasoning without enforcing direct global alignment between modalities. Extensive experiments on six datasets demonstrate that AptM-GCD consistently achieves SoTA performance across both fine-grained and generic benchmarks. Moreover, the proposed framework exhibits strong generalization ability, delivering consistent gains under unimodal and class-imbalanced GCD settings.

Comments: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2611.12975 [cs.CV]

(or arXiv:2611.12975v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.12975

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhixiang Chi [view email] [v1] Sun, 8 Nov 2026 04:01:26 UTC (8,687 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery, by Wei Zhang and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Existing methods entangle global tags and local attributes in a shared representation, making attributes unreliable.
  • AEL interacts attribute embeddings with patch-level visual tokens to identify reliable attribute regions and extract discriminative local evidence.
  • MPL converts fine-grained textual evidence into visual prompts injected into a multimodal prompt transformer.
  • AptM-GCD achieves SoTA on six datasets for both fine-grained and generic benchmarks, with robustness under unimodal and class-imbalanced settings.

Highlights and analysis are generated automatically and may contain errors. Check the original source.