# Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts

arXiv: https://arxiv.org/abs/2508.20488 · HTML: https://mlsanity.com/paper/2508.20488/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 30 of 41)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [Train in Germany, Test in The USA: Making 3D Object Detectors Generalize](https://mlsanity.com/paper/2005.08139/) (2020)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2108.11127/) (2021)
- [Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16470/) (2021)
- [DELTA: degradation-free fully test-time adaptation](https://mlsanity.com/paper/2301.13018/) (2023)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [LATR: 3D Lane Detection from Monocular Images with Transformer](https://mlsanity.com/paper/2308.04583/) (2023)
- [MonoCD: Monocular 3D Object Detection with Complementary Depths](https://mlsanity.com/paper/2404.03181/) (2024)
- [MonoGround: Detecting Monocular 3D Objects from the Ground](https://mlsanity.com/paper/2206.07372/) (2022)

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

- [Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation](https://mlsanity.com/paper/2605.23257/) (2026)

## Abstract (arXiv)

Accurate monocular 3D object detection (M3OD) is pivotal for safety-critical applications like autonomous driving, yet its reliability deteriorates significantly under real-world domain shifts caused by environmental or sensor variations. To address these shifts, Test-Time Adaptation (TTA) methods have emerged, enabling models to adapt to target distributions during inference. While prior TTA approaches recognize the positive correlation between low uncertainty and high generalization ability, they fail to address the dual uncertainty inherent to M3OD: semantic uncertainty (ambiguous class predictions) and geometric uncertainty (unstable spatial localization). To bridge this gap, we propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD. Through a convex optimization lens, we introduce an innovative convex structure of the focal loss and further derive a novel unsupervised version, enabling label-agnostic uncertainty weighting and balanced learning for high-uncertainty objects. In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues, reducing uncertainty from the unstable 3D representation. This dual-branch mechanism forms a complementary loop: enhanced spatial perception improves semantic classification, and robust semantic predictions further refine spatial understanding. Extensive experiments demonstrate the superiority of DUO over existing methods across various datasets and domain shift types.