GAZE LATENT SUPPORT VECTOR MACHINE FOR IMAGE CLASSIFICATION

Xin Wang 1 Nicolas Thome 1 Matthieu Cord 1
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper deals with image categorization from weak supervision, e.g. global image labels. We propose to improve the region selection performed in latent variable models such as Latent Support Vector Machine (LSVM) by leveraging human eye movement features collected from an eye-tracker device. We introduce a new model, Gaze Latent Support Vector Machine (G-LSVM), whose region selection during training is biased toward regions with a large gaze density ratio. On this purpose, the training objective is enriched with a gaze loss, from which we derive a convex upper bound, leading to a Concave-Convex Procedure (CCCP) optimization scheme. Experiments show that G-LSVM significantly outperforms LSVM in both object detection and action recognition problems on PASCAL VOC 2012. We also show that our G-LSVM is even slightly better than a model trained from bounding box annotations, while gaze labels are much cheaper to collect.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [31 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01342580
Contributor : Xin Wang <>
Submitted on : Wednesday, July 6, 2016 - 1:26:15 PM
Last modification on : Thursday, March 21, 2019 - 1:14:04 PM

File

GAZE_LATENT_SUPPORT_VECTOR_MAC...
Files produced by the author(s)

Identifiers

Citation

Xin Wang, Nicolas Thome, Matthieu Cord. GAZE LATENT SUPPORT VECTOR MACHINE FOR IMAGE CLASSIFICATION. IEEE International Conference on Image Processing (ICIP), IEEE, Sep 2016, Phoenix, AZ, United States. ⟨10.1109/ICIP.2016.7532354⟩. ⟨hal-01342580⟩

Share

Metrics

Record views

126

Files downloads

261