Learning by Reconstruction Produces Uninformative Features For Perception

17 February 2024

Papers citing "Learning by Reconstruction Produces Uninformative Features For Perception"

7 / 7 papers shown

Title
Beyond [cls]: Exploring the true potential of Masked Image Modeling representations Marcin Przewiȩźlikowski Randall Balestriero Wojciech Jasiński Marek 'Smieja Bartosz Zieliñski 69 0 0 04 Dec 2024
An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving S. Mohammed Alp Argun Nicolas Bonnotte Gerd Ascheid OffRL 28 0 0 02 Sep 2024
Many Perception Tasks are Highly Redundant Functions of their Input Data Rahul Ramesh Anthony Bisulco Ronald W. DiTullio Linran Wei Vijay Balasubramanian Kostas Daniilidis Pratik Chaudhari 41 2 0 18 Jul 2024
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks Sophia Sirko-Galouchenko Alexandre Boulch Spyros Gidaris Andrei Bursuc Antonín Vobecký Patrick Pérez Renaud Marlet 3DPC 32 7 0 22 Apr 2024
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank Q. Garrido Randall Balestriero Laurent Najman Yann LeCun SSL 48 72 0 05 Oct 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 305 7,434 0 11 Nov 2021
End-to-end optimization of nonlinear transform codes for perceptual quality Johannes Ballé Valero Laparra Eero P. Simoncelli 70 244 0 18 Jul 2016