WiSE-OD: Benchmarking Robustness in Infrared Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Medeiros, Heitor R., Belal, Atif, Aminbeidokhti, Masih, Granger, Eric, Pedersoli, Marco
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917171024625664
author Medeiros, Heitor R.
Belal, Atif
Aminbeidokhti, Masih
Granger, Eric
Pedersoli, Marco
author_facet Medeiros, Heitor R.
Belal, Atif
Aminbeidokhti, Masih
Granger, Eric
Pedersoli, Marco
contents Object detection (OD) in infrared (IR) imagery is critical for low-light and nighttime applications. However, the scarcity of large-scale IR datasets forces models to rely on weights pre-trained on RGB images. While fine-tuning on IR improves accuracy, it often compromises robustness under distribution shifts due to the inherent modality gap between RGB and IR. To address this, we introduce LLVIP-C and FLIR-C, two cross-modality out-of-distribution (OOD) benchmarks built by applying corruptions to standard IR datasets. Additionally, to fully leverage the complementary knowledge from RGB and infrared-trained models, we propose WiSE-OD, a weight-space ensembling method with two variants: WiSE-OD$_{ZS}$, which combines RGB zero-shot and IR fine-tuned weights, and WiSE-OD$_{LP}$, which blends zero-shot and linear probing. Evaluated using four RGB-pretrained detectors and two robust baselines on our benchmark and in the real-world out-of-distribution M3FD dataset, our WiSE-OD improves robustness across modalities and to corruption in synthetic and real-world distribution shifts without any additional training or inference costs. Our code is available at: https://github.com/heitorrapela/wiseod.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18925
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WiSE-OD: Benchmarking Robustness in Infrared Object Detection
Medeiros, Heitor R.
Belal, Atif
Aminbeidokhti, Masih
Granger, Eric
Pedersoli, Marco
Computer Vision and Pattern Recognition
Artificial Intelligence
Object detection (OD) in infrared (IR) imagery is critical for low-light and nighttime applications. However, the scarcity of large-scale IR datasets forces models to rely on weights pre-trained on RGB images. While fine-tuning on IR improves accuracy, it often compromises robustness under distribution shifts due to the inherent modality gap between RGB and IR. To address this, we introduce LLVIP-C and FLIR-C, two cross-modality out-of-distribution (OOD) benchmarks built by applying corruptions to standard IR datasets. Additionally, to fully leverage the complementary knowledge from RGB and infrared-trained models, we propose WiSE-OD, a weight-space ensembling method with two variants: WiSE-OD$_{ZS}$, which combines RGB zero-shot and IR fine-tuned weights, and WiSE-OD$_{LP}$, which blends zero-shot and linear probing. Evaluated using four RGB-pretrained detectors and two robust baselines on our benchmark and in the real-world out-of-distribution M3FD dataset, our WiSE-OD improves robustness across modalities and to corruption in synthetic and real-world distribution shifts without any additional training or inference costs. Our code is available at: https://github.com/heitorrapela/wiseod.
title WiSE-OD: Benchmarking Robustness in Infrared Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.18925