Explore In-Context Learning for 3D Point Cloud Understanding
We propose Point-In-Context (PIC), the first framework adopting the in-context learning paradigm for 3D point cloud understanding. Specifically, we set up an extensive dataset of point cloud pairs with four fundamental tasks to achieve in-context ability. We propose effective designs that facilitate the training and solve the inherited information leakage problem. PIC shows its excellent learning capacity, achieves comparable results with single-task models, and outperforms multitask models on all four tasks. Besides, it shows good generalization ability to out-of-distribution samples and unseen tasks and has great potential via selecting higher-quality prompts. We hope it paves the way for further exploration of in-context learning in the 3D modalities.
Dec 10, 2023
Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation
This paper presents a joint Caption Grounding and Generation (CGG) framework for instance-level open vocabulary segmentation. The main contributions are: (1) using fine-grained object nouns in captions to improve grounding with object queries. (2) using captions as supervision signals to extract rich information from other words helps identify novel categories. To our knowledge, this paper is the first to unify segmentation and caption generation for open vocabulary learning. The proposed framework significantly improves OVIS and OSPS and comparable results on OVOD without pre-training on large-scale datasets.
Oct 2, 2023