# DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction

arXiv: https://arxiv.org/abs/2407.17779 · HTML: https://mlsanity.com/paper/2407.17779/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels](https://mlsanity.com/paper/1905.05040/) (2019)
- [OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding](https://mlsanity.com/paper/2305.10764/) (2023)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Meta Label Correction for Noisy Label Learning](https://mlsanity.com/paper/1911.03809/) (2019)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)
- [Webly Supervised Learning of Convolutional Networks](https://mlsanity.com/paper/1505.01554/) (2015)
- [MeshNet: Mesh Neural Network for 3D Shape Representation](https://mlsanity.com/paper/1811.11424/) (2018)
- [ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving](https://mlsanity.com/paper/1811.12222/) (2018)
- [ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks](https://mlsanity.com/paper/2005.03788/) (2020)
- [DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs](https://mlsanity.com/paper/1905.03465/) (2019)
- [Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing](https://mlsanity.com/paper/2012.13538/) (2020)

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

- [MCA: 2D-3D Retrieval with Noisy Labels via Multi-level Adaptive Correction and Alignment](https://mlsanity.com/paper/2508.06104/) (2025)

## Abstract (arXiv)

With the recent burst of 2D and 3D data, cross-modal retrieval has attracted increasing attention recently. However, manual labeling by non-experts will inevitably introduce corrupted annotations given ambiguous 2D/3D content. Though previous works have addressed this issue by designing a naive division strategy with hand-crafted thresholds, their performance generally exhibits great sensitivity to the threshold value. Besides, they fail to fully utilize the valuable supervisory signals within each divided subset. To tackle this problem, we propose a Divide-and-conquer 2D-3D cross-modal Alignment and Correction framework (DAC), which comprises Multimodal Dynamic Division (MDD) and Adaptive Alignment and Correction (AAC). Specifically, the former performs accurate sample division by adaptive credibility modeling for each sample based on the compensation information within multimodal loss distribution. Then in AAC, samples in distinct subsets are exploited with different alignment strategies to fully enhance the semantic compactness and meanwhile alleviate over-fitting to noisy labels, where a self-correction strategy is introduced to improve the quality of representation. Moreover. To evaluate the effectiveness in real-world scenarios, we introduce a challenging noisy benchmark, namely Objaverse-N200, which comprises 200k-level samples annotated with 1156 realistic noisy labels. Extensive experiments on both traditional and the newly proposed benchmarks demonstrate the generality and superiority of our DAC, where DAC outperforms state-of-the-art models by a large margin. (i.e., with +5.9% gain on ModelNet40 and +5.8% on Objaverse-N200).