Prompt-Free Universal Region Proposal Network
Qihong Tang, Changhan Liu, Shaofeng Zhang, Wenbin Li, Qi Fan, Yang Gao

TL;DR
This paper introduces PF-RPN, a prompt-free, adaptable region proposal network that identifies potential objects across diverse domains without external prompts, effective even with limited data.
Contribution
The novel PF-RPN framework eliminates the need for prompts, enabling flexible object proposal generation across various applications and datasets.
Findings
Effective with limited data (e.g., 5% MS COCO)
Applicable to diverse domains like underwater and remote sensing
Validated on 19 datasets with strong results
Abstract
Identifying potential objects is critical for object recognition and analysis across various computer vision applications. Existing methods typically localize potential objects by relying on exemplar images, predefined categories, or textual descriptions. However, their reliance on image and text prompts often limits flexibility, restricting adaptability in real-world scenarios. In this paper, we introduce a novel Prompt-Free Universal Region Proposal Network (PF-RPN), which identifies potential objects without relying on external prompts. First, the Sparse Image-Aware Adapter (SIA) module performs initial localization of potential objects using a learnable query embedding dynamically updated with visual features. Next, the Cascade Self-Prompt (CSP) module identifies the remaining potential objects by leveraging the self-prompted learnable embedding, autonomously aggregating informative…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Multimodal Machine Learning Applications · Domain Adaptation and Few-Shot Learning
