Leveraging 2D Foundation Priors for Generalized Category Discovery under Test-Time Adaptation in 3D LiDAR Segmentation
cs.CV, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances
- Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking
- APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- DINOv2: Learning Robust Visual Features without Supervision
- Generalized Category Discovery in Semantic Segmentation
- DINOv3
- Generalized Category Discovery via Token Manifold Capacity Learning
- Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
- Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation
- Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
- UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather
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