TL;DR
UIU-Net introduces a nested U-Net architecture with multi-scale and multi-level features, enhancing infrared small object detection by effectively capturing contrast and detail, outperforming existing methods.
Contribution
The paper proposes a novel 'U-Net in U-Net' framework with deep supervision and cross attention modules, enabling better feature learning for infrared small object detection from scratch.
Findings
Outperforms state-of-the-art methods on SIRST and Synthetic datasets.
Demonstrates strong generalization on infrared video sequences.
Effective in enhancing contrast and detail for small object detection.
Abstract
Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for obtaining precise object contrast information. For this reason, we in this paper propose a simple and effective ``U-Net in U-Net'' framework, UIU-Net for short, and detect small objects in infrared images. As the name suggests, UIU-Net embeds a tiny U-Net into a larger U-Net backbone, enabling the multi-level and multi-scale representation learning of objects. Moreover, UIU-Net can be trained from scratch, and the learned features can enhance global and local contrast information effectively. More specifically, the UIU-Net model is divided into…
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
MethodsConvolution · *Communicated@Fast*How Do I Communicate to Expedia? · Concatenated Skip Connection · Max Pooling · U-Net
