Dear all,
Antoine Chassang will tell us about his work on face detection during his internship at the LISA lab. The talk will be held at the usual place AA3195 starting from 13.30 next Wednesday (26 Nov).
Hope to see many of you at the talk! - Cho
=== - Speaker: Antoine Chassang - Date/Time: 26 Nov (Wed) 13.30 - 14.30 - Place: AA3195 - Title: Face Detection - Abstract:
Whereas the state of the art is relying on viewpoint-specialized models which need additional pose-related annotations, we trained convolutional networks on a large dataset (700k faces extracted from Google Images) to learn invariance to pose. We evaluated our method on FDDB, a standard benchmark for face detection, and we show that we can achieve state of the art performance. To speed up the inference, we investigated model compression using a teacher-student formulation where the student network learns to reproduce the teacher output. The compressed model is deeper and thinner, with less parameters than the teacher.
Afficher les réponses par date
Dear all,
Antoine will tell us about this work on face detection and building a classroom of teacher and student neural networks, starting at 13.30 tomorrow.
Hope to see many of you there! - K
On Sat, Nov 22, 2014 at 2:49 PM, Kyung Hyun Cho cho.k.hyun@gmail.com wrote:
Dear all,
Antoine Chassang will tell us about his work on face detection during his internship at the LISA lab. The talk will be held at the usual place AA3195 starting from 13.30 next Wednesday (26 Nov).
Hope to see many of you at the talk!
- Cho
===
- Speaker: Antoine Chassang
- Date/Time: 26 Nov (Wed) 13.30 - 14.30
- Place: AA3195
- Title: Face Detection
- Abstract:
Whereas the state of the art is relying on viewpoint-specialized models which need additional pose-related annotations, we trained convolutional networks on a large dataset (700k faces extracted from Google Images) to learn invariance to pose. We evaluated our method on FDDB, a standard benchmark for face detection, and we show that we can achieve state of the art performance. To speed up the inference, we investigated model compression using a teacher-student formulation where the student network learns to reproduce the teacher output. The compressed model is deeper and thinner, with less parameters than the teacher.