Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Sicre, Ronan"'
Autor:
Zhang, Hanwei, Cheng, Luo, He, Qisong, Huang, Wei, Li, Renjue, Sicre, Ronan, Huang, Xiaowei, Hermanns, Holger, Zhang, Lijun
Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML tasks, classif
Externí odkaz:
http://arxiv.org/abs/2405.14210
Autor:
Sicre, Ronan, Zhang, Hanwei, Dejasmin, Julien, Daaloul, Chiheb, Ayache, Stéphane, Artières, Thierry
This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system learns an
Externí odkaz:
http://arxiv.org/abs/2404.15037
This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation. However, i
Externí odkaz:
http://arxiv.org/abs/2404.15024
Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this observati
Externí odkaz:
http://arxiv.org/abs/2404.14996
CAM-based methods are widely-used post-hoc interpretability method that produce a saliency map to explain the decision of an image classification model. The saliency map highlights the important areas of the image relevant to the prediction. In this
Externí odkaz:
http://arxiv.org/abs/2404.01964
Autor:
Zhao, Zhengyu, Zhang, Hanwei, Li, Renjue, Sicre, Ronan, Amsaleg, Laurent, Backes, Michael, Li, Qi, Shen, Chao
Transferable adversarial examples raise critical security concerns in real-world, black-box attack scenarios. However, in this work, we identify two main problems in common evaluation practices: (1) For attack transferability, lack of systematic, one
Externí odkaz:
http://arxiv.org/abs/2310.11850
Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a saliency ma
Externí odkaz:
http://arxiv.org/abs/2301.07002
Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two common limitations in existing evaluations. First, different methods are of
Externí odkaz:
http://arxiv.org/abs/2211.09565
Publikováno v:
In Computer Vision and Image Understanding November 2024 248
Part-based image classification aims at representing categories by small sets of learned discriminative parts, upon which an image representation is built. Considered as a promising avenue a decade ago, this direction has been neglected since the adv
Externí odkaz:
http://arxiv.org/abs/1704.03755