Научны(е)й руководител(и)ь : Matthieu CORD

Со-руководитель : THOME Nicolas

Gaze-Based Weakly Supervised Localization for Image Classification: Application to Visual Recognition in a Food Dataset

In this dissertation, we discuss how to use the human gaze data to improve the performance of the weak supervised learning model in image classification. The background of this topic is in the era of rapidly growing information technology. As a consequence, the data to analyze is also growing dramatically. Since the amount of data that can be annotated by the human cannot keep up with the amount of data itself, current well-developed supervised learning approaches may confront bottlenecks in the future. In this context, the use of weak annotations for high-performance learning methods is worthy of study. Specifically, we try to solve the problem from two aspects: One is to propose a more time-saving annotation, human eye-tracking gaze, as an alternative annotation with respect to the traditional time-consuming annotation, e.g. bounding box. The other is to integrate gaze annotation into a weakly supervised learning scheme for image classification. This scheme benefits from the gaze annotation for inferring the regions containing the target object. A useful property of our model is that it only exploits gaze for training, while the test phase is gaze free. This property further reduces the demand of annotations. The two isolated aspects are connected together in our models, which further achieve competitive experimental results.

Публикации 2015-2021

• 2021
  • Y. Yang, H. Jiang, G. Zhang, X. Wang, Y. Lv, X. Li, S. Fdida, G. Xie : “S2H: Hypervisor as a Setter within Virtualized Network I/O for VM Isolation on Cloud Platform”, Computer Networks, vol. 201, pp. 108577, (Elsevier) (2021)
• 2019
  • K. Qiu, J. Zhao, X. Wang, X. Fu, S. Secci : “Efficient Recovery Path Computation for Fast Reroute in Large-scale Software Defined Networks”, IEEE Journal on Selected Areas in Communications, vol. 37 (8), pp. 1755-1768, (Institute of Electrical and Electronics Engineers) (2019)
  • K. Qiu, J. Yuan, J. Zhao, X. Wang, S. Secci, X. Fu : “FastRule: Efficient Flow Entry Updates for TCAM-based OpenFlow Switches”, IEEE Journal on Selected Areas in Communications, vol. 37 (3), pp. 484-498,, (Institute of Electrical and Electronics Engineers) (2019)
• 2018
  • K. Qiu, J. Yuan, J. Zhao, X. Wang, S. Secci, X. Fu : “Fast Lookup Is Not Enough: Towards Efficient and Scalable Flow Entry Updates for TCAM-Based OpenFlow Switches”, 38^th IEEE International Conference on Distributed Computing Systems (ICDCS), Vienna, Austria (2018)
• 2017
  • X. Wang : “Gaze-Based Weakly Supervised Localization for Image Classification: Application to Visual Recognition in a Food Dataset”, диссертация, Защита диссертаций 29.09.2017, Научны(е)й руководител(и)ь Cord, Matthieu, Со-руководитель : Thome, Nicolas (2017)
  • X. Wang, N. Thome, M. Cord : “Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region Selection”, Pattern Recognition, vol. 72, pp. 59-71, (Elsevier) (2017)
  • K. Qiu, S. Huang, Q. Xu, J. Zhao, X. Wang, S. Secci : “ParaCon: A Parallel Control Plane for Scaling Up Path Computation in SDN”, IEEE Transactions on Network and Service Management, vol. 14 (4), pp. 978-990, (IEEE) (2017)
• 2016
  • X. Wang, N. Thome, M. Cord : “GAZE LATENT SUPPORT VECTOR MACHINE FOR IMAGE CLASSIFICATION”, IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, United States (2016)
• 2015
  • X. Wang, D. Kumar, N. Thome, M. Cord, F. Precioso : “RECIPE RECOGNITION WITH LARGE MULTIMODAL FOOD DATASET”, IEEE International Conference on Multimedia & Expo (ICME), workshop CEA, Turin, Italy (2015)