Olivier Bachem

@OlivierBachem

Research Scientist at in the Brain team in Zurich. Before that, PhD at Zurich, Co-Founder of , and CPO at .

Vrijeme pridruživanja: ožujak 2013.

Tweetovi

Blokirali ste korisnika/cu @OlivierBachem

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

  1. Prikvačeni tweet
    11. lip 2019.

    I am excited and honored that we received the Best Paper Award with "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations" (). W/ , S. Bauer, , , ,

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    6. sij

    We distill key components for pre-training representations at scale: BigTransfer ("BiT") achieves SOTA on many benchmarks with ResNet, e.g. 87.8% top-1 on ImageNet (86.4% with only 25 images/class) and 99.3% on CIFAR-10 (97.6% with only 10 images/class).

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet

    How much supervision do you need to learn disentangled representations? Turns out, not that much! Joint work with , S. Bauer, , and . Accepted at

    Poništi
  4. proslijedio/la je Tweet
    20. pro 2019.

    Our work which critically investigates the role of mutual information in self-supervised representation learning was accepted to . w/ J. Djolonga

    Poništi
  5. proslijedio/la je Tweet
    13. pro 2019.

    It was great collaborating with you Paul, happy to hear you had a great time!

    Poništi
  6. proslijedio/la je Tweet

    3) Are Disentangled Representations Helpful for Abstract Visual Reasoning? Poster 28. Joint work with , , and If you want to talk to me, I'll be at poster 34! (3/3)

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet

    2) On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset: Poster 35. Joint work with Gondal, Bauer S., , et al. (2/3)

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    Big disentanglement line-up today 17:00 at ! 1) On the Fairness of Disentangled Representations: Poster 34. Joint work with Abbati G., , Bauer S., and (1/3)

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet

    Are disentangled representations helpful for abstract visual reasoning? Come find out later today during the afternoon poster session at 17:00, poster board 28. This is joint work with , , and

    Poništi
  10. proslijedio/la je Tweet
    9. pro 2019.

    Join , Piotr Stanczyk, , and now at our booth to learn the latest about the Google Research Football Environment (). Also, learn about Dataset Search () with !

    Poništi
  11. proslijedio/la je Tweet
    27. stu 2019.

    Check out Semantic Bottleneck GAN: 1) Generating semantic label maps from scratch and 2) using SPADE to translate them into realistic images yields SOTA unconditional generation of high-resolution complex scenes!

    Poništi
  12. proslijedio/la je Tweet
    27. stu 2019.

    In our recent collaboration with we show how to generate realistic complex scenes from scratch! While the problem is extremely challenging, we show how to achieve SOTA in unconditional generation and improve conditional generation using SPADE

    Poništi
  13. 26. stu 2019.

    Check out v2.0 of Google Research Football which includes a game server where your agent can challenge other agents!

    Poništi
  14. proslijedio/la je Tweet
    21. stu 2019.

    Interested in visual representation learning, but tired of ImageNet, Cifar, & VOC? Remote Sensing is a research area with many important applications. To dig deeper check out our paper with

    Poništi
  15. 20. stu 2019.

    I'm excited that disentanglement_lib now supports the Unsupervised Disentanglement Ranking (UDR) method thanks to a code contribution by , and their co-authors. Code: Paper:

    Poništi
  16. proslijedio/la je Tweet
    15. stu 2019.

    On the Fairness of Disentangled Representations (poster Thu Dec 12th) by , Gabriele Abbati, , Stefan Bauer, with

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet

    Joint work with fantastic collaborators Gabriele Abbati, , Stefan Bauer, and from , , , and .

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    Interested in Fairness and Representation Learning? The code to reproduce our paper “On the Fairness of Disentangled Representations” is now available at

    Prikaži ovu nit
    Poništi
  19. 29. lis 2019.

    Excited that our paper "Are Disentangled Representations Helpful for Abstract Visual Reasoning?" () is accepted to with code released at . With , & .

    Poništi
  20. proslijedio/la je Tweet
    25. lis 2019.

    I wrote up my experience training PPO on the GFootball environment, reproducing the paper's results, and some fun stuff to do with a trained model here:

    Poništi
  21. 17. lis 2019.

    Check out our recent benchmark for representation learning!

    Poništi

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:

    ·