3D-BBDA: Backpropagation-Free Black-Box Domain Adaptation for Robust 3D Point Cloud Recognition
cs.CV, cs.CE, cs.RO
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://visdomlab.github.io/3D_BBDA
Terminology
Sources
- FAST3D: Flow-Aware Self-Training for 3D Object Detectors
- PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
- Revisiting Batch Normalization For Practical Domain Adaptation
- DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
- Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
- Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs