ResearchTrend.AI
S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention

S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention

Pierre Guetschel
Thomas Moreau
Michael Tangermann
ArXivPDFHTML

Papers citing "S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention"

2 / 2 papers shown
Title
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
Ananya Kumar
Aditi Raghunathan
Robbie Jones
Tengyu Ma
Percy Liang
OODD
102
655
0
21 Feb 2022
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Alexei Baevski
Henry Zhou
Abdel-rahman Mohamed
Michael Auli
SSL
197
5,734
0
20 Jun 2020