# AdaCo: Overcoming Visual Foundation Model Noise in 3D Semantic Segmentation via Adaptive Label Correction

arXiv: https://arxiv.org/abs/2412.18255 · HTML: https://mlsanity.com/paper/2412.18255/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 41 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [Error-Bounded Correction of Noisy Labels](https://mlsanity.com/paper/2011.10077/) (2020)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [Towards Label-free Scene Understanding by Vision Foundation Models](https://mlsanity.com/paper/2306.03899/) (2023)
- [Training Convolutional Networks with Noisy Labels](https://mlsanity.com/paper/1406.2080/) (2014)
- [The Lov'asz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks](https://mlsanity.com/paper/1705.08790/) (2017)

## Built on by (most cited first, 6 of 6)

- [SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts](https://mlsanity.com/paper/2503.06467/) (2025)
- [LOSC: LiDAR Open-voc Segmentation Consolidator](https://mlsanity.com/paper/2507.07605/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning](https://mlsanity.com/paper/2512.16461/) (2025)
- [IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2604.01361/) (2026)
- [Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers](https://mlsanity.com/paper/2610.00855/) (2026)

## Abstract (arXiv)

Recently, Visual Foundation Models (VFMs) have shown a remarkable generalization performance in 3D perception tasks. However, their effectiveness in large-scale outdoor datasets remains constrained by the scarcity of accurate supervision signals, the extensive noise caused by variable outdoor conditions, and the abundance of unknown objects. In this work, we propose a novel label-free learning method, Adaptive Label Correction (AdaCo), for 3D semantic segmentation. AdaCo first introduces the Cross-modal Label Generation Module (CLGM), providing cross-modal supervision with the formidable interpretive capabilities of the VFMs. Subsequently, AdaCo incorporates the Adaptive Noise Corrector (ANC), updating and adjusting the noisy samples within this supervision iteratively during training. Moreover, we develop an Adaptive Robust Loss (ARL) function to modulate each sample's sensitivity to noisy supervision, preventing potential underfitting issues associated with robust loss. Our proposed AdaCo can effectively mitigate the performance limitations of label-free learning networks in 3D semantic segmentation tasks. Extensive experiments on two outdoor benchmark datasets highlight the superior performance of our method.