Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Frameworkby Ryan Lucas, Rahul MazumderFirst…
Streamlining Prediction in Bayesian Deep Learningby Rui Li, Marcus Klasson, Arno Solin, Martin TrappFirst submitted…
Soft-TransFormers for Continual Learningby Haeyong Kang, Chang D. YooFirst submitted to arxiv on: 25 Nov…
On the Surprising Effectiveness of Attention Transfer for Vision Transformersby Alexander C. Li, Yuandong Tian,…
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformersby Shravan Venkatraman, Jaskaran…
ScaleKD: Strong Vision Transformers Could Be Excellent Teachersby Jiawei Fan, Chao Li, Xiaolong Liu, Anbang…
Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environmentsby Deegan Atha, Xianmei…
GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noiseby Moseli Mots'oehli,…
Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptationby Xiwen Wei, Guihong Li, Radu MarculescuFirst…
LASER: Attention with Exponential Transformationby Sai Surya Duvvuri, Inderjit S. DhillonFirst submitted to arxiv on:…