中文
相关论文

相关论文: AIR-Net: Adaptive and Implicit Regularization Neur…

200 篇论文

While the Implicit Bias(or Implicit Regularization) of standard loss functions has been studied, the optimization geometry induced by discriminative metric-learning objectives remains largely unexplored.To the best of our knowledge, this…

机器学习 · 计算机科学 2026-04-13 Jiawen Li

In the past, optimization-based registration models have used spatially-varying regularization to account for deformation variations in different image regions. However, deep learning-based registration models have mostly relied on…

图像与视频处理 · 电气工程与系统科学 2023-03-14 Junyu Chen , Yihao Liu , Yufan He , Yong Du

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

机器学习 · 计算机科学 2015-03-03 Sergey Ioffe , Christian Szegedy

Motion detection has been widely used in many applications, such as surveillance and robotics. Due to the presence of the static background, a motion video can be decomposed into a low-rank background and a sparse foreground. Many…

计算机视觉与模式识别 · 计算机科学 2023-04-12 Jing Qin , Biyun Xie

In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high-level inference using purely data-driven neural networks.…

计算机视觉与模式识别 · 计算机科学 2018-09-11 Suhas Lohit , Rajhans Singh , Kuldeep Kulkarni , Pavan Turaga

Convex regularizers are often used for sparse learning. They are easy to optimize, but can lead to inferior prediction performance. The difference of $\ell_1$ and $\ell_2$ ($\ell_{1-2}$) regularizer has been recently proposed as a nonconvex…

机器学习 · 计算机科学 2017-06-21 Quanming Yao , James T. Kwok , Xiawei Guo

Axiomatic information retrieval (IR) seeks a set of principle properties desirable in IR models. These properties when formally expressed provide guidance in the search for better relevance estimation functions. Neural ranking models…

信息检索 · 计算机科学 2019-04-16 Corby Rosset , Bhaskar Mitra , Chenyan Xiong , Nick Craswell , Xia Song , Saurabh Tiwary

This letter proposes to estimate low-rank matrices by formulating a convex optimization problem with non-convex regularization. We employ parameterized non-convex penalty functions to estimate the non-zero singular values more accurately…

计算机视觉与模式识别 · 计算机科学 2016-04-14 Ankit Parekh , Ivan W. Selesnick

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

计算机视觉与模式识别 · 计算机科学 2019-09-25 Jiayun Wang , Patrick Virtue , Stella X. Yu

Given a limited number of entries from the superposition of a low-rank matrix plus the product of a known fat compression matrix times a sparse matrix, recovery of the low-rank and sparse components is a fundamental task subsuming…

多智能体系统 · 计算机科学 2013-10-01 Morteza Mardani , Gonzalo Mateos , Georgios B. Giannakis

Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Jonas Ngnawe , Marianne Abemgnigni Njifon , Jonathan Heek , Yann Dauphin

Neural networks have achieved tremendous success in a large variety of applications. However, their memory footprint and computational demand can render them impractical in application settings with limited hardware or energy resources. In…

机器学习 · 计算机科学 2022-10-19 Steffen Schotthöfer , Emanuele Zangrando , Jonas Kusch , Gianluca Ceruti , Francesco Tudisco

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

机器学习 · 计算机科学 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Parameter-efficient fine-tuning (PEFT) of pre-trained foundation models is increasingly attracting interest in medical imaging due to its effectiveness and computational efficiency. Among these methods, Low-Rank Adaptation (LoRA) is a…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Ghassen Baklouti , Julio Silva-Rodríguez , Jose Dolz , Houda Bahig , Ismail Ben Ayed

Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have been studied…

机器学习 · 计算机科学 2025-08-25 Tom Jacobs , Chao Zhou , Rebekka Burkholz

Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization…

计算机视觉与模式识别 · 计算机科学 2019-06-27 Alex Hernández-García , Peter König

Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fields including computer vision, data mining, signal…

计算机视觉与模式识别 · 计算机科学 2014-10-24 Xiaowei Zhou , Can Yang , Hongyu Zhao , Weichuan Yu

Many applications require recovering a matrix of minimal rank within an affine constraint set, with matrix completion a notable special case. Because the problem is NP-hard in general, it is common to replace the matrix rank with the…

机器学习 · 计算机科学 2015-07-08 Bo Xin , David Wipf

Despite several algorithmic advances in the training of convolutional neural networks (CNNs) over the years, their generalization capabilities are still subpar across several pertinent domains, particularly within open-set tasks often found…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Colton R. Crum , Adam Czajka

Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However, the ability to perform few or zero-shot adaptation to novel…

机器学习 · 计算机科学 2020-10-14 Samarth Sinha , Karsten Roth , Anirudh Goyal , Marzyeh Ghassemi , Hugo Larochelle , Animesh Garg