Jérôme Rony

[Jérôme Rony @jerome_rony]

Check out our new paper on adversarial attacks for semantic segmentation! https://t.co/TDkpmk2bYN
Using a proximal splitting, we generate small perturbations (e.g. ‖δ‖_∞ < 1/255) for deep segmentation models, with high pixel success rates.

[Jérôme Rony @jerome_rony]

@YouTubeInsider @DeanoSauruz @earthklaans You are trying to be precise but you are mistaken in what GenAI means. Tranformers are not GenAI per se, they are a type of neural network building block that can be used in so called GenAI, but does not have to be.

[Jérôme Rony @jerome_rony]

@raymondh Second one: it implies that h(x) is the default case, and g(x) is a specific one conditioned on test. I think it is also dependent on what test is: are we expecting test(x) to be mostly true ?

[Jose Dolz @josedolz_ets]

If you are at #CVPR2023 drop by to see our posters for tomorrow.

AM: 289 - A strong baseline for generalized few-shot semantic segmentation.

PM: Class adaptive network calibration.

with @IsmailBenAyed1 @bing_bingyuan @jerome_rony @adrian_galdran Sina Hajimiri and Malik Boudiaf

[Jérôme Rony @jerome_rony]

@DrewLinsley That's the issue, even C&W is not strong enough to assess adversarial robustness

[Jérôme Rony @jerome_rony]

@DrewLinsley I can see a major issue here: \ell_2 PGD (and even C&W) is known to be weak to evaluate a model's robustness. There are much more reliable options (and less expensive than C&W) now: APGD, DDN, FMN, ALMA to name a few.

[Jérôme Rony @jerome_rony]

@Vicnent @MathisHammel @JacquesDelamar2 Sur les tests de Mathis, c'est environ 15% plus lent avec la condition (testé sur ma machine car CoderPad n'est pas très régulier sur les run-times)

[Jérôme Rony @jerome_rony]

@Vicnent @MathisHammel @JacquesDelamar2 Ça va beaucoup dépendre de la longueur de la meilleure solution: si elle est significativement plus courte que la liste initiale, ça n'affecte pas la complexité

[Jérôme Rony @jerome_rony]

@CSProfKGD Oh I did that in the first comment to start the discussion.

[Jérôme Rony @jerome_rony]

@MathisHammel IMO la façon la plus simple de s'assurer que le cas négatif soit clair.

[Jérôme Rony @jerome_rony]

@colorado_reed We did! We worked on a problem that is not novel, but also somewhat understudied IMO.

[Jérôme Rony @jerome_rony]

@CSProfKGD No worries, just sharing my experience 🙂 Even though I sometimes end up disappointed for my own papers, I'm extremely grateful of the work ACs do!

[Jérôme Rony @jerome_rony]

@Ana_Kay31 @_davyben @CultureCrave Should have clarified: Tick-Tock is the long version of Mountains in the Interstellar expanded album

[Jérôme Rony @jerome_rony]

@Ana_Kay31 @_davyben @CultureCrave You should check the extended version called "Tick-Tock" in the expanded version of the album!

[Jérôme Rony @jerome_rony]

@CVPR @mahmoudnafifi Is there going to be an additional week for review?

[Jérôme Rony @jerome_rony]

@benjamin_warner @wightmanr The EMA step could be even faster using:
>>> torch._foreach_mul_(ema_tensors, decay)
in the first step.

[Jérôme Rony @jerome_rony]

@le_science4all @NeurIPSConf Ce n'est pas obligatoire d'écrire ce paragraphe pour NeurIPS.

[Jérôme Rony @jerome_rony]

@AMurderOfDucks @gabrielpeyre You can use it to minimize a sum of nonsmooth functions (e.g. infinity norm) by iteratively minimizing each using their respective proximity operator https://t.co/P2uIxkkZeO