HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
Heitor Rapela Medeiros, Fidel A. Guerrero Pena, Masih Aminbeidokhti,, Thomas Dubail, Eric Granger, Marco Pedersoli

TL;DR
HalluciDet is a novel IR-RGB image translation model that enhances object detection by focusing on detection loss reduction rather than image reconstruction, improving detection accuracy without needing RGB data.
Contribution
The paper introduces HalluciDet, a new image translation approach that leverages privileged RGB detector information to improve IR-based object detection.
Findings
Outperforms state-of-the-art translation methods in detection accuracy.
Enhances object detection in IR images without access to RGB data.
Shows significant improvements across various datasets.
Abstract
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal application, such as pedestrian detection from aerial images, with a considerable shift in data distribution between infrared (IR) to visible (RGB) images, a translation focused on generation might lead to poor performance as the loss focuses on irrelevant details for the task. In this paper, we propose HalluciDet, an IR-RGB image translation model for object detection. Instead of focusing on reconstructing the original image on the IR modality, it seeks to reduce the detection loss of an RGB detector, and therefore avoids the need to access RGB data. This model produces a new image representation that enhances objects of interest in the scene and…
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
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information· youtube
Taxonomy
TopicsUser Authentication and Security Systems · Digital Media Forensic Detection · Anomaly Detection Techniques and Applications
Methods1x1 Convolution · Focal Loss · RetinaNet · Region Proposal Network · Softmax · Convolution · RoIPool · Faster R-CNN · Feature Pyramid Network · Non Maximum Suppression
