SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08479 · ECCV · 2022

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

Min Sun, Cheng Sun, Ping-Chung Yu, Rgb-D Pair

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for training are typically limited in quantity compared to the 2D images counterpart. In this work, we deal with the data scarcity challenge of 3D tasks by transferring knowledge from strong 2D models via RGB-D images. Specifically, we utilize a strong and welltrained semantic segmentation model for 2D images to augment RGB-D images with pseudo-label. The augmented dataset can then be used to pre-train 3D models. Finally, by simply fine-tuning on a few labeled 3D instances, our method already outperforms existing state-of-the-art that is tailored for 3D label efficiency. We also show that the results of meanteacher and entropy minimization can be improved by our pre-training, suggesting that the transferred knowledge is helpful in semi-supervised setting. We verify the effectiveness of our approach on two popular 3D models and three different tasks. On ScanNet official evaluation, we establish new state-of-the-art semantic segmentation results on the data-efficient track. Code: https://github.com/bryanyu1997/Data-Efficient-3D-Learner.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08479")
get_code_for_paper("2203.08479")
have("2203.08479")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.08479.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.08479.svg)](https://syntology.ai/paper/2203.08479)

Connect an agent — have() is free.