Search Results for author:
Found 5 papers, 0 papers with code
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification
In order to tackle these issues, we turn to the recently proposed parameter-efficient tuning methods, such as VPT, which updates only the newly added prompt parameters while keeping the pre-trained backbone frozen.
LPN: Language-guided Prototypical Network for few-shot classification
Few-shot classification aims to adapt to new tasks with limited labeled examples.
PVP: Pre-trained Visual Parameter-Efficient Tuning
Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks.
Ranked #4 on
Image Classification
on VTAB-1k
(using extra training data)
Truncated Cauchy Non-negative Matrix Factorization
Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because the loss function is sensitive to outliers.
MahNMF: Manhattan Non-negative Matrix Factorization
This paper presents Manhattan NMF (MahNMF) which minimizes the Manhattan distance between $X$ and $W^T H$ for modeling the heavy tailed Laplacian noise.
