Papers › AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning
Oddy Virgantara Putra, Kohichi Ogata, Eko Mulyanto Yuniarno, Mauridhi Hery Purnomo
Manual annotation of large-scale point cloud datasets is laborious due to their irregular structure. While cross-modal contrastive learning methods such as CrossPoint and CrossNet have progressed in utilizing multimodal data for self-supervised learning, they still suffer from instability during training caused by the static weighting of intra-modal (IM) and cross-modal (CM) losses. These static weights fail to account for the varying convergence rates of different modalities. We propose AdaCrossNet, a novel self-supervised learning framework for point cloud understanding that utilizes a dynamic weight adjustment mechanism for IM and CM contrastive learning. AdaCrossNet learns representations by simultaneously enhancing the alignment between 3-D point clouds and their associated 2D- rendered images within a common latent space. Our dynamic weight adjustment mechanism adaptively balances the contributions of IM and CM losses during training, guided by the convergence behavior of each modality. To ensure stability in the training process, we employ an exponentially weighted moving average (EWMA) to smooth the weight updates. We experimented with benchmark datasets, ModelNet40, ShapeNetPart, and ScanObjectNN. The results demonstrate that AdaCrossNet achieves superiority over other methods, with 91.4% accuracy on the ModelNet40 classification task. While on the segmentation task, AdaCrossNet achieved the mIoU score of 85.1% on the ShapeNetPart segmentation task. Additionally, AdaCrossNet, when combined with the DGCNN backbone, showed significant improvements in the ScanObjectNN dataset with 82.1% accuracy. Our method boosts training efficiency while increasing the generalizability of the learned representations across downstream tasks
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Part Segmentation | ShapeNet-Part | AdaCrossNet | Class Average IoU | 85.1 | #65 of 67 | Archive leaderboard | report |
| 3D Point Cloud Classification | ModelNet40 | AdaCrossNet | Overall Accuracy | 93.1 | #75 of 111 | Archive leaderboard | report |
| 3D Point Cloud Linear Classification | ModelNet40 | AdaCrossNet | Overall Accuracy | 91.8 | #7 of 20 | Archive leaderboard | report |
| 3D Point Cloud Linear Classification | ScanObjectNN | AdaCrossNet | Overall Accuracy | 82.1 | #2 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections