Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Simon Loic"'
With the recent success of generative models in image and text, the evaluation of generative models has gained a lot of attention. Whereas most generative models are compared in terms of scalar values such as Frechet Inception Distance (FID) or Incep
Externí odkaz:
http://arxiv.org/abs/2405.01611
This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classifier's prediction for a given image. Our proposed method, Text-to-Imag
Externí odkaz:
http://arxiv.org/abs/2309.07944
Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science. These models require large image databases like LAION-2B, which contain two billion images. At this scal
Externí odkaz:
http://arxiv.org/abs/2303.12733
Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks cannot be used directly in a counterfactual explanation perspecti
Externí odkaz:
http://arxiv.org/abs/2303.09962
Publikováno v:
In Computer Vision and Image Understanding December 2024 249
Autor:
Colomb-Cotinat, Mélanie a, ⁎, Jouzeau, Amélie b, Pedrono, Gaëlle a, Chabaud, Aurélie c, Martin, Christian c, Poujol, Isabelle a, Maugat, Sylvie a, Dugravot, Lory b, Dumartin, Catherine c, Berger-Carbonne, Anne a, Simon, Loïc b, Dortet, Laurent d
Publikováno v:
In Infectious Diseases Now February 2025 55(1)
Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent diffusion models.
Externí odkaz:
http://arxiv.org/abs/2203.15636
Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain. However, further works revealed severe inadeq
Externí odkaz:
http://arxiv.org/abs/2109.07920
Machine learning tools are becoming increasingly powerful and widely used. Unfortunately membership attacks, which seek to uncover information from data sets used in machine learning, have the potential to limit data sharing. In this paper we conside
Externí odkaz:
http://arxiv.org/abs/2108.00800
Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website {\small \url{ http://thispersondoesnotexist.com}}, taunts users with GAN generated images that
Externí odkaz:
http://arxiv.org/abs/2107.06018