DAC: 2D-3D Retrieval With Noisy Labels Via Divide-and-conquer Alignment And Correction

Abstract

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 strate

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keygan2024dac

Related papers

• MCA: 2D-3D Retrieval With Noisy Labels Via Multi-level Adaptive Correction And Alignment (2025)0.00
• Describe, Adapt And Combine: Empowering CLIP Encoders For Open-set 3D Object Retrieval (2025)2.51
• Correspondence-free Domain Alignment For Unsupervised Cross-domain Image Retrieval (2023)9.23
• PC\(^2\): Pseudo-classification Based Pseudo-captioning For Noisy Correspondence Learning In Cross-modal Retrieval (2024)9.23
• Error-corrected Margin-based Deep Cross-modal Hashing For Facial Image Retrieval (2020)8.09
• ROCA: Robust CAD Model Retrieval And Alignment From A Single Image (2021)12.61
• SCA3D: Enhancing Cross-modal 3D Retrieval Via 3D Shape And Caption Paired Data Augmentation (2025)4.17
• Neighbor-aware Instance Refining With Noisy Labels For Cross-modal Retrieval (2025)2.26