Try   HackMD

ConvNets and humans are not biased towards the same information in images

by Alban Marie (IETR - Vaader) - 2021.03.04

tags: VAADER Reading Group

Abstract

Nowadays, it is well established that ConvNets are able to achieve incredible performance on complex vision task such as classification, object recognition or semantic segmentation. A common thought is that humans and ConvNets are able to solve these tasks by learning increasingly complex representations of object shapes. However, recent studies show that humans and ConvNets have indeed very different strategies by not being biased towards the same information in images. To this end, authors propose a stylized version of ImageNet , allowing ConvNets to learn images representation used by humans easier.

Slides

Presentation and Discussions

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

Last changed by 
 
VAADER - Image & IA - Lecture Group
VAADER - Image & IA - Lecture Group
0
194

Read more

[Vaader "AI for Image" Reading Group](https://hackmd.io/@imageia/H1QtmJiCD)

Organization contact [name= F. Lemarchand (flemarch at insa-rennes.fr)] Next Meeting(s) 🌴 The reading group is in holidays. 🌴 See you in september! Past Meetings 2021 Karol Desnos: Paper Digest: "Dynamic Neural Networks: A Survey"

Oct 14, 2021
Supervised learning to approximate model observer in task-based measure of image quality

by Meriem Bayou-Outtas (IETR-VAADER) - 2021.06.16 Abstract The ability of an observer to perform a specific task on images, produced by a given medical imaging systems, defines an objective measure of image quality. If the observer is “numerical”, can deep learning methods “do the job”? What we found in the literature? Some papers rise this issue and propose to approximate the Ideal Observer for performing tasks detection and localization. Related Material [1] Approximating the Ideal Observer and Hotelling Observer for Binary Signal Detection Tasks by Use of Supervised Learning Methods, IEEE TMI 2019 [2] Approximating the Ideal Observer for Joint Signal Detection and Localization Tasks by use of Supervised Learning Methods, IEEE TMI 2020

Jul 5, 2021
Paper Digest: "Dynamic Neural Networks: A Survey"

by Karol DESNOS (IETR-VAADER) - 2021.07.01 02:00 PM Abstract Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to different inputs, leading to notable advantages in terms of accuracy, computational efficiency, adaptiveness, etc. In this survey, we comprehensively review this rapidly developing area by dividing dynamic networks into three main categories: 1) instance-wise dynamic models that process each instance with data-dependent architectures or parameters; 2) spatial-wise dynamic networks that conduct adaptive computation with respect to different spatial locations of image data and 3) temporal-wise dynamic models that perform adaptive inference along the temporal dimension for sequential data such as videos and texts. The important research problems of dynamic networks, e.g., architecture design, decision making scheme, optimization technique and applications, are reviewed systematically. Finally, we discuss the open problems in this field together with interesting future research directions Related Material Dynamic Neural Networks: A Survey Slides

Jul 5, 2021
A gentle introduction to hardware architectures for DNN acceleration

by Mickaël Dardaillon (IETR - Vaader) - 2021.05.06 - 2:00 PM Abstract "The synergy between the large datasets in the cloud and the numerous computers that power it has enabled remarkable advancements in machine learning, especially in DNNs. […] That changed in 2013 when a projection in which Google users searched by voice for three minutes per day using speech recognition DNNs would double Google datacenters’ computation demands." This presentation will introduce the concepts behind the hardware architectures used to support current growth in machine learning, including GPUs and TPUs. Related Material A Domain-Specific Architecture for Deep Neural Networks

May 18, 2021
Read more from VAADER - Image & IA - Lecture Group
Published on HackMD