Abstract of paper. Add TeX formulas using the following formats: $In-line Formula$ or $$Block Formula$$.

Search author profile by first, middle and last name or email address. All authors must have an OpenReview profile.

Describe changes since last TMLR submission. Add TeX formulas using the following formats: $In-line Formula$ or $$Block Formula$$.

Beyond those reflected in the authors' OpenReview profile, disclose relationships (notably financial) of any author with entities that could potentially be perceived to influence what you wrote in the submitted work, during the last 36 months prior to this submission. This would include engagements with commercial companies or startups (sabbaticals, employments, stipends), honorariums, donations of hardware or cloud computing services. Enter "N/A" if this question isn't applicable to your situation.

If the submission reports experiments involving human subjects, provide information available on the approval of these experiments, such as from an Institutional Review Board (IRB). Enter "N/A" if this question isn't applicable to your situation.

If a version of this submission was previously rejected by TMLR, give the OpenReview link to the original TMLR submission (which must still be anonymous) and describe the changes below.

Check if this is a regular length submission, i.e. the main content (all pages before references and appendices) is 12 pages or less. Note that the review process may take significantly longer for papers longer than 12 pages.

All supplementary material must be self-contained and zipped into a single file. Note that supplementary material will be visible to reviewers and the public throughout and after the review period, and ensure all material is anonymized. The maximum file size is 100MB.

Title of paper. Add TeX formulas using the following formats: $In-line Formula$ or $$Block Formula$$.

Optionally, you may submit a link to code for your work.

Optionally, you may submit a link to a video summarizing your work.

Certifications are meant to highlight particularly notable accepted submissions. Notably, it is through certifications that we make room for more speculative/editorial judgement on the significance and potential for impact of accepted submissions. Certification selection is the responsibility of the AE, however you are asked to submit your recommendation.

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Andreas Peter Steiner, Alexander Kolesnikov, Xiaohua Zhai, Ross Wightman, Jakob Uszkoreit, Lucas Beyer