SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.06440 · 2019

Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation

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

Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied. In this paper, we investigate a new perspective of facial landmark detection and demonstrate it leads to further notable improvement. Given that any face images can be factored into space of style that captures lighting, texture and image environment, and a style-invariant structure space, our key idea is to leverage disentangled style and shape space of each individual to augment existing structures via style translation. With these augmented synthetic samples, our semi-supervised model surprisingly outperforms the fully-supervised one by a large margin. Extensive experiments verify the effectiveness of our idea with state-of-the-art results on WFLW, 300W, COFW, and AFLW datasets. Our proposed structure is general and could be assembled into any face alignment frameworks. The code is made publicly available at https://github.com/thesouthfrog/stylealign.

For agents

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

get_harvested_code_for_paper("1908.06440")
get_code_for_paper("1908.06440")
have("1908.06440")

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

curl https://syntology.ai/api/ran/1908.06440.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.06440.svg)](https://syntology.ai/paper/1908.06440)

Connect an agent — have() is free.