Visual point cloud forecasting enables scalable autonomous driving
In contrast to extensive studies on general vision pre-training for scalable visual
autonomous driving remains seldom explored. Visual autonomous driving applications …
autonomous driving remains seldom explored. Visual autonomous driving applications …
Reverse engineering self-supervised learning
Understanding the learned representation and underlying mechanisms of Self-Supervised
Learning (SSL) often poses a challenge. In this paper, we 'reverse engineer'SSL, conducting …
Learning (SSL) often poses a challenge. In this paper, we 'reverse engineer'SSL, conducting …
Language-based action concept spaces improve video self-supervised learning
K Ranasinghe, MS Ryoo - Advances in Neural Information …, 2023 - proceedings.neurips.cc
Recent contrastive language image pre-training has led to learning highly transferable and
robust image representations. However, adapting these models to video domain with …
robust image representations. However, adapting these models to video domain with …
Multiple physics pretraining for physical surrogate models
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic
pretraining approach for physical surrogate modeling. MPP involves training large surrogate …
pretraining approach for physical surrogate modeling. MPP involves training large surrogate …
Scaling Riemannian diffusion models
Riemannian diffusion models draw inspiration from standard Euclidean space diffusion
models to learn distributions on general manifolds. Unfortunately, the additional geometric …
models to learn distributions on general manifolds. Unfortunately, the additional geometric …
Virchow2: Scaling self-supervised mixed magnification models in pathology
Foundation models are rapidly being developed for computational pathology applications.
However, it remains an open question which factors are most important for downstream …
However, it remains an open question which factors are most important for downstream …
Vip: A differentially private foundation model for computer vision
Artificial intelligence (AI) has seen a tremendous surge in capabilities thanks to the use of
foundation models trained on internet-scale data. On the flip side, the uncurated nature of …
foundation models trained on internet-scale data. On the flip side, the uncurated nature of …
Masked autoencoders are scalable learners of cellular morphology
Inferring biological relationships from cellular phenotypes in high-content microscopy
screens provides significant opportunity and challenge in biological research. Prior results …
screens provides significant opportunity and challenge in biological research. Prior results …
CL-MAE: Curriculum-Learned Masked Autoencoders
Masked image modeling has been demonstrated as a powerful pretext task for generating
robust representations that can be effectively generalized across multiple downstream tasks …
robust representations that can be effectively generalized across multiple downstream tasks …
Fantastic gains and where to find them: On the existence and prospect of general knowledge transfer between any pretrained model
Training deep networks requires various design decisions regarding for instance their
architecture, data augmentation, or optimization. In this work, we find these training …
architecture, data augmentation, or optimization. In this work, we find these training …