Cihang Xie

@cihangxie

Ph.D. student at Johns Hopkins

Baltimore, MD
cihangxie.github.io
Vrijeme pridruživanja: srpanj 2014.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @cihangxie

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @cihangxie

  1. proslijedio/la je Tweet
    3. pro 2019.

    This video explains AdvProp from ! This technique leverages Adversarial Examples for ImageNet classification by using separate Batch Normalization layers for clean and adversarial mini-batches.

    29 proslijeđenih tweetova 86 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    25. stu 2019.

    Can adversarial examples improve image recognition? Check out our recent work: AdvProp, achieving ImageNet top-1 accuracy 85.5% (no extra data) with adversarial examples! Arxiv: Checkpoints:

    84 proslijeđena tweeta 376 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    25. stu 2019.

    Pretrained checkpoints in Pytorch: h/t to

    9 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    25. stu 2019.

    AdvProp improves accuracy for a wide range of image models, from small to large. But the improvement seems bigger when the model is larger.

    3 proslijeđena tweeta 39 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    25. stu 2019.

    As a data augmentation method, adversarial examples are more general than other image processing techniques. So I expect AdvProp to be useful everywhere (language, structured data etc.), not just image recognition.

    14 proslijeđenih tweetova 94 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    25. stu 2019.

    Many of us tried to use adversarial examples as data augmentation and observed a drop in accuracy. And it seems that simply using two BatchNorms overcomes this mysterious drop in accuracy.

    1 reply 9 proslijeđenih tweetova 62 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    25. stu 2019.

    AdvProp: One weird trick to use adversarial examples to reduce overfitting. Key idea is to use two BatchNorms, one for normal examples and another one for adversarial examples. Significant gains on ImageNet and other test sets.

    Can adversarial examples improve image recognition? Check out our recent work: AdvProp, achieving ImageNet top-1 accuracy 85.5% (no extra data) with adversarial examples! Arxiv: Checkpoints:
    158 proslijeđenih tweetova 567 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    8. velj 2019.

    FAIR has released code for the robust ImageNet model by Cihang Xie et al:

    70 proslijeđenih tweetova 278 korisnika označava da im se sviđa
    Poništi
  9. 12. pro 2017.

    Check out Whova Event and Conference App and save $100 for your event app!

    Poništi
  10. proslijedio/la je Tweet
    8. pro 2017.

    Cihang Xie presenting the runner-up defense: randomization at test time

    8 proslijeđenih tweetova 29 korisnika označava da im se sviđa
    Poništi
  11. 12. kol 2015.

    Using uberPOOL, I saved $12.42. Get ready for a summer with a weekly surprise from .

    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi

@cihangxie još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·