most citedMany Perception Tasks are Highly Redundant Functions of their Input Data

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2025

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations

Anthony Bisulco, Rahul Ramesh, Randall Balestriero +1

Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning…

cs.CV2024★ 1 cited

Many Perception Tasks are Highly Redundant Functions of their Input Data

Rahul Ramesh, Anthony Bisulco, Ronald W. DiTullio +4

We show that many perception tasks, from visual recognition, semantic segmentation, optical flow, depth estimation to vocalization discrimination, are highly redundant functions of…