Amir Roshan Zamir

Biographie

Amir Zamir is a Tenure-Track Assistant Professor of Computer Science at the Swiss Federal Institute of Technology in Lausanne (EPFL). Prior to EPFL, he spent time at Stanford, UC Berkeley, and UCF. His research interests are broadly in computer vision, machine learning, perception-for-robotics, and AI. He has been recognized with CVPR (2018) Best Paper Award, CVPR (2016) Best Student Paper Award, CVPR (2020) Best Paper Award Nomination, and NVIDIA Pioneering Research Award (2018), among others. His research has been covered by various press outlets, such as The New York Times or Forbes.

Official source

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Unités associées

Chargement

Cours enseignés par cette personne

Chargement

Domaines de recherche associés

Chargement

Publications associées

Chargement

Personnes menant des recherches similaires

Chargement

3D Common Corruptions and Data Augmentation

Andrei Atanov, Oguzhan Fatih Kar, Amir Roshan Zamir, Shuqing Teresa Yeo

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations is that, unlike existing approaches such as Common Corruptions [27], the geometry of the scene is incorporated in the transformations - thus leading to corruptions that are more likely to occur in the real world. We also introduce a set of semantic corruptions (e.g. natural object occlusions. See Fig. 1). We show these transformations are 'efficient' (can be computed on-the-fly), 'extendable' (can be applied on most image datasets), expose vulnerability of existing models, and can effectively make models more robust when employed as '3D data augmentation' mechanisms. The evaluations on several tasks and datasets suggest incorporating 3D information into benchmarking and training opens up a promising direction for robustness research.

IEEE COMPUTER SOC2022

Chargement

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Andrei Atanov, Roman Christian Bachmann, David Mizrahi, Amir Roshan Zamir

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB image (hence "multi-modal"), and II) its training objective accordingly includes predicting multiple outputs besides the RGB image (hence "multi-task"). We make use of masking (across image patches and input modalities) to make training MultiMAE tractable as well as to ensure cross-modality predictive coding is indeed learned by the network. We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks. In particular, the same exact pre-trained network can be flexibly used when additional information besides RGB images is available or when no information other than RGB is available - in all configurations yielding competitive to or significantly better results than the baselines. To avoid needing training datasets with multiple modalities and tasks, we train MultiMAE entirely using pseudo labeling, which makes the framework widely applicable to any RGB dataset. The experiments are performed on multiple transfer tasks (image classification, semantic segmentation, depth estimation) and datasets (ImageNet, ADE20K, Taskonomy, Hypersim, NYUv2). The results show an intriguingly impressive capability by the model in cross-modal/task predictive coding and transfer.

SPRINGER INTERNATIONAL PUBLISHING AG2022

Chargement

, ,

This paper introduces a pipeline to parametrically sample and render static multi-task vision datasets from comprehensive 3D scans from the real-world. In addition to enabling interesting lines of research, we show the tooling and generated data suffice to train robust vision models. Familiar architectures trained on a generated starter dataset reached state-of-the-art performance on multiple common vision tasks and benchmarks, despite having seen no benchmark or non-pipeline data. The depth estimation network outperforms MiDaS and the surface normal estimation network is the first to achieve human-level performance for in-the-wild surface normal estimation-at least according to one metric on the OASIS benchmark. The Dockerized pipeline with CLI, the (mostly python) code, PyTorch dataloaders for the generated data, the generated starter dataset, download scripts and other utilities are all available through our project website.

IEEE2021

Chargement