Chinmay Prabhakar

Chinmay Prabhakar

Auto-generated profile, based on publicly available information

Chinmay Prabhakar

University of Zürich

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 October 2024
Verified
Book Chapter
Closed access
PDF file
CPChinmay Prabhakar
Chinmay Prabhakar
SSSuprosanna Shit
Suprosanna Shit
FMFabio Musio
Fabio Musio
KYKaiyuan Yang
Kaiyuan Yang
TATamaz Amiranashvili
Tamaz Amiranashvili
BMBjoern Menze
Bjoern Menze

1 October 2023
Verified
Book Chapter
Closed access
PDF file
CPChinmay Prabhakar
Chinmay Prabhakar
HLHongwei Bran Li
Hongwei Bran Li
JPJohannes C. Paetzold
Johannes C. Paetzold
TLTimo Loehr
Timo Loehr
CNChen Niu
Chen Niu
BMBjoern Menze
Bjoern Menze

23 July 2026 in NEJM AI
Verified
Journal Article
Closed access
KYKaiyuan Yang
Kaiyuan Yang
FMFabio Musio
Fabio Musio
YMYihui Ma
Yihui Ma
NJNorman Juchler
Norman Juchler
JPJohannes C. Paetzold
Johannes C. Paetzold
BMBjoern Menze
Bjoern Menze

7 February 2026 in Neuroscience Informatics
Verified
Journal Article
Open access
FMFabio Musio
Fabio Musio
NJNorman Juchler
Norman Juchler
KYKaiyuan Yang
Kaiyuan Yang
SSSuprosanna Shit
Suprosanna Shit
CPChinmay Prabhakar
Chinmay Prabhakar
SHSven Hirsch
Sven Hirsch

2 October 2026
Verified
Book Chapter
Closed access
PDF file
CPChinmay Prabhakar
Chinmay Prabhakar
BWBastian Wittmann
Bastian Wittmann
TATamaz Amiranashvili
Tamaz Amiranashvili
PBPaul Büschl
Paul Büschl
EREzequiel de la Rosa
Ezequiel de la Rosa
SSSuprosanna Shit
Suprosanna Shit

15 May 2023 in arXiv
Verified
Preprint
Open access
PDF file
CPChinmay Prabhakar
Chinmay Prabhakar
HLHongwei Bran Li
Hongwei Bran Li
JYJiancheng Yang
Jiancheng Yang
SSSuprosana Shit
Suprosana Shit
BWBenedikt Wiestler
Benedikt Wiestler
BMBjoern Menze
Bjoern Menze
Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning technique that employs a patch-masking strategy to learn a meaningful latent space. In this paper, we focus on improving ViT-AE (nicknamed ViT-AE++) for a more effective representation of 2D and 3D medical images. We propose two new loss functions to enhance the representation during training. The first loss term aims to improve self-reconstruction by considering the structured dependencies and indirectly improving the representation. The second loss term leverages contrastive loss to optimize the representation from two randomly masked views directly. We extended ViT-AE++ to a 3D fashion for volumetric medical images as an independent contribution. We extensively evaluate ViT-AE++ on both natural images and medical images, demonstrating consistent improvement over vanilla ViT-AE and its superiority over other contrastive learning approaches. Codes are here: https://github.com/chinmay5/vit_ae_plus_plus.git.