CVLGIVSep 29, 2020

SwiftFace: Real-Time Face Detection

arXiv:2009.13743v1Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for fast face detection in applications like mobile apps and security, though it is incremental as it focuses on speed rather than a new paradigm.

The paper tackles the problem of real-time face detection by introducing SwiftFace, a novel deep learning model designed solely for speed, which performs 30% faster than current state-of-the-art models.

Computer vision is a field of artificial intelligence that trains computers to interpret the visual world in a way similar to that of humans. Due to the rapid advancements in technology and the increasing availability of sufficiently large training datasets, the topics within computer vision have experienced a steep growth in the last decade. Among them, one of the most promising fields is face detection. Being used daily in a wide variety of fields; from mobile apps and augmented reality for entertainment purposes, to social studies and security cameras; designing high-performance models for face detection is crucial. On top of that, with the aforementioned growth in face detection technologies, precision and accuracy are no longer the only relevant factors: for real-time face detection, speed of detection is essential. SwiftFace is a novel deep learning model created solely to be a fast face detection model. By focusing only on detecting faces, SwiftFace performs 30% faster than current state-of-the-art face detection models. Code available at https://github.com/leo7r/swiftface

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes