SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.11567 · 2024

Positional Prompt Tuning for Efficient 3D Representation Learning

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

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we explore parameter-efficient fine-tuning (PEFT) through the lens of prompts and adapters, introducing a straightforward yet effective method called PPT for point cloud analysis. PPT incorporates increased patch tokens and trainable positional encoding while keeping most pre-trained model parameters frozen. Extensive experiments validate that PPT is both effective and efficient. Our proposed method of PEFT tasks, namely PPT, with only 1.05M of parameters for training, gets state-of-the-art results in several mainstream datasets, such as 95.01% accuracy in the ScanObjectNN OBJ_BG dataset. Codes and weights will be released at https://github.com/zsc000722/PPT.

For agents

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

get_harvested_code_for_paper("2408.11567")
get_code_for_paper("2408.11567")
have("2408.11567")

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

curl https://syntology.ai/api/ran/2408.11567.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.11567.svg)](https://syntology.ai/paper/2408.11567)

Connect an agent — have() is free.