SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03518 · CVPR · 2024

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

Jun Wang, Shouhong Ding, Peixian Chen, Ran Yi, Lizhuang Ma, Ke Fan, Ruixin Zhang, Siming Huang, Yingyi Zhang, Sichen Chen

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

Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to deploy on edge computing platforms. Those transformer-based models that require fewer resources are prone to under-fitting due to their smaller scale and thus perform notably worse than their larger counterparts. Given this conundrum, we introduce SD-Pose, a new self-distillation method for improving the performance of small transformer-based models. To mitigate the problem of under-fitting, we design a transformer module named Multi-Cycled Transformer(MCT) based on multiple-cycled forwards to more fully exploit the potential of small model parameters. Further, in order to prevent the additional inference compute-consuming brought by MCT, we introduce a self-distillation scheme, extracting the knowledge from the MCT module to a naive forward model. Specifically, on the MSCOCO validation dataset, SDPose-T obtains 69.7% mAP with 4.4M parameters and 1.8 GFLOPs. Furthermore, SDPose-S-V2 obtains 73.5% mAP on the MSCOCO validation dataset with 6.2M parameters and 4.7 GFLOPs, achieving a new state-of-the-art among predominant tiny neural network methods.

For agents

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

get_harvested_code_for_paper("2404.03518")
get_code_for_paper("2404.03518")
have("2404.03518")

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

curl https://syntology.ai/api/ran/2404.03518.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.03518.svg)](https://syntology.ai/paper/2404.03518)

Connect an agent — have() is free.