# WiSE-OD: Benchmarking Robustness in Infrared Object Detection

arXiv: https://arxiv.org/abs/2507.18925 · HTML: https://mlsanity.com/paper/2507.18925/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks](https://mlsanity.com/paper/2009.12664/) (2020)
- [COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts](https://mlsanity.com/paper/2307.12730/) (2023)
- [Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data](https://mlsanity.com/paper/2211.11925/) (2022)
- [HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information](https://mlsanity.com/paper/2310.04662/) (2023)
- [Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras](https://mlsanity.com/paper/2209.11335/) (2022)
- [Visual Modality Prompt for Adapting Vision-Language Object Detectors](https://mlsanity.com/paper/2412.00622/) (2024)
- [Benchmarking performance of object detection under image distortions in an uncontrolled environment](https://mlsanity.com/paper/2210.15999/) (2022)
- [Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge](https://mlsanity.com/paper/2404.01492/) (2024)
- [Benchmarking the Robustness of UAV Tracking Against Common Corruptions](https://mlsanity.com/paper/2403.11424/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation](https://mlsanity.com/paper/2605.15906/) (2026)

## Abstract (arXiv)

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-ODZS, which combines RGB zero-shot and IR fine-tuned weights, and WiSE-ODLP, 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.