English
Related papers

Related papers: Neural network task specialization via domain cons…

200 papers

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower learning rates,…

Machine Learning · Statistics 2022-10-19 Lakshmi Annamalai , Chetan Singh Thakur

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models…

Robotics · Computer Science 2017-03-22 Josh Tobin , Rachel Fong , Alex Ray , Jonas Schneider , Wojciech Zaremba , Pieter Abbeel

Modern deep neural network (DNN) trainings utilize various training techniques, e.g., nonlinear activation functions, batch normalization, skip-connections, etc. Despite their effectiveness, it is still mysterious how they help accelerate…

Machine Learning · Computer Science 2024-03-05 Cheng Chen , Junjie Yang , Yi Zhou

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications.…

Machine Learning · Computer Science 2021-02-18 Wenyu Zhang , Mohamed Ragab , Ramon Sagarna

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

Machine Learning · Statistics 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable…

Computation and Language · Computer Science 2023-02-21 Guangtao Zeng , Wei Lu

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired…

Machine Learning · Statistics 2023-12-29 Tim G. J. Rudner , Sanyam Kapoor , Shikai Qiu , Andrew Gordon Wilson

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

Machine Learning · Computer Science 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Xander Coetzer , Arné Schreuder , Anna Sergeevna Bosman

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Xiaotong Li , Yongxing Dai , Yixiao Ge , Jun Liu , Ying Shan , Ling-Yu Duan

We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Reiichiro Nakano

Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference. Language-specific modeling methods show promise in reducing interference. However, they often rely on heuristics to…

Computation and Language · Computer Science 2024-04-18 Shaomu Tan , Di Wu , Christof Monz

Deep learning has been widely used for hyperspectral pixel classification due to its ability of generating deep feature representation. However, how to construct an efficient and powerful network suitable for hyperspectral data is still…

Computer Vision and Pattern Recognition · Computer Science 2019-04-17 Jingzhou Chen , Siyu Chen , Peilin Zhou , Yuntao Qian

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Machine Learning · Computer Science 2024-10-08 Gus Kristiansen , Mark Sandler , Andrey Zhmoginov , Nolan Miller , Anirudh Goyal , Jihwan Lee , Max Vladymyrov

Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a…

Computation and Language · Computer Science 2020-10-29 Alan Ramponi , Barbara Plank

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Xiaotong Li , Zixuan Hu , Jun Liu , Yixiao Ge , Yongxing Dai , Ling-Yu Duan

Understanding Deep Neural Network (DNN) performance in changing conditions is essential for deploying DNNs in safety critical applications with unconstrained environments, e.g., perception for self-driving vehicles or medical image…

Computer Vision and Pattern Recognition · Computer Science 2022-02-09 Molly O'Brien , Julia Bukowski , Mathias Unberath , Aria Pezeshk , Greg Hager

We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Zak Murez , Soheil Kolouri , David Kriegman , Ravi Ramamoorthi , Kyungnam Kim

Machine learning systems must adapt to data distributions that evolve over time, in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces. We consider gradual domain adaptation, where…

Machine Learning · Computer Science 2020-02-27 Ananya Kumar , Tengyu Ma , Percy Liang

The potential of large language models (LLMs) to simultaneously perform a wide range of natural language processing (NLP) tasks has been the subject of extensive research. Although instruction tuning has proven to be a data-efficient method…

Computation and Language · Computer Science 2023-10-25 Chufan Shi , Yixuan Su , Cheng Yang , Yujiu Yang , Deng Cai