# Contrast-Guided Cross-Modal Distillation for Thermal Object Detection

arXiv: https://arxiv.org/abs/2511.01435 · HTML: https://mlsanity.com/paper/2511.01435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [Cross-Modality Fusion Transformer for Multispectral Object Detection](https://mlsanity.com/paper/2111.00273/) (2021)
- [Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks](https://mlsanity.com/paper/2009.12664/) (2020)
- [Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2112.02991/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation](https://mlsanity.com/paper/2108.07482/) (2021)
- [Thermal Infrared Colorization via Conditional Generative Adversarial Network](https://mlsanity.com/paper/1810.05399/) (2018)
- [Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention](https://mlsanity.com/paper/2104.14374/) (2021)
- [IR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translation](https://mlsanity.com/paper/1806.09565/) (2018)

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

- [FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection](https://mlsanity.com/paper/2606.11572/) (2026)

## Abstract (arXiv)

Robust perception at night remains challenging for thermal-infrared detection: low contrast and weak high-frequency cues lead to duplicate, overlapping boxes, missed small objects, and class confusion. Prior remedies either translate TIR to RGB and hope pixel fidelity transfers to detection -- making performance fragile to color or structure artifacts -- or fuse RGB and TIR at test time, which requires extra sensors, precise calibration, and higher runtime cost. Both lines can help in favorable conditions, but do not directly shape the thermal representation used by the detector. We keep mono-modality inference and tackle the root causes during training. Specifically, we introduce training-only objectives that sharpen instance-level decision boundaries by pulling together features of the same class and pushing apart those of different classes -- suppressing duplicate and confusing detections -- and that inject cross-modal semantic priors by aligning the student's multi-level pyramid features with an RGB-trained teacher, thereby strengthening texture-poor thermal features without visible input at test time. In experiments, our method outperformed prior approaches and achieved state-of-the-art performance.