English
Related papers

Related papers: Improving Layer-wise Adaptive Rate Methods using T…

200 papers

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all…

Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust…

Machine Learning · Computer Science 2023-12-11 Lassi Meronen , Martin Trapp , Andrea Pilzer , Le Yang , Arno Solin

Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Kevin Duarte , Yogesh S. Rawat , Mubarak Shah

We propose a new \emph{Transformed Risk Minimization} (TRM) framework as an extension of classical risk minimization. In TRM, we optimize not only over predictive models, but also over data transformations; specifically over distributions…

Machine Learning · Computer Science 2023-10-09 Evangelos Chatzipantazis , Stefanos Pertigkiozoglou , Kostas Daniilidis , Edgar Dobriban

Deep neural networks (DNNs) often suffer from the overconfidence issue, where incorrect predictions are made with high confidence scores, hindering the applications in critical systems. In this paper, we propose a novel approach called…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Yijun Liu , Jiequan Cui , Zhuotao Tian , Senqiao Yang , Qingdong He , Xiaoling Wang , Jingyong Su

Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels. Previous approaches…

Machine Learning · Computer Science 2024-04-10 Gaotang Li , Jiarui Liu , Wei Hu

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…

Machine Learning · Computer Science 2021-03-18 Lusine Abrahamyan , Yiming Chen , Giannis Bekoulis , Nikos Deligiannis

Most existing works focus on improving robustness against adversarial attacks bounded by a single $l_p$ norm using adversarial training (AT). However, these AT models' multiple-norm robustness (union accuracy) is still low, which is crucial…

Machine Learning · Computer Science 2024-09-24 Enyi Jiang , Gagandeep Singh

While Large language models (LLMs) have advanced natural language processing tasks, their growing computational and memory demands make deployment on resource-constrained devices like mobile phones increasingly challenging. In this paper,…

Machine Learning · Computer Science 2025-02-13 Yiping Wang , Hanxian Huang , Yifang Chen , Jishen Zhao , Simon Shaolei Du , Yuandong Tian

Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this…

Computation and Language · Computer Science 2025-10-28 Yasmin Moslem , Muhammad Hazim Al Farouq , John D. Kelleher

For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Christoph Kamann , Burkhard Güssefeld , Robin Hutmacher , Jan Hendrik Metzen , Carsten Rother

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…

Computer Vision and Pattern Recognition · Computer Science 2017-12-25 Lorenz Berger , Eoin Hyde , M. Jorge Cardoso , Sebastien Ourselin

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Yang Luo , Zhineng Chen , Peng Zhou , Zuxuan Wu , Xieping Gao , Yu-Gang Jiang

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Machine Learning · Computer Science 2022-02-22 Ming-Chang Chiu , Xuezhe Ma

Recently, deep neural networks have become to be used in a variety of applications. While the accuracy of deep neural networks is increasing, the confidence score, which indicates the reliability of the prediction results, is becoming more…

Machine Learning · Computer Science 2021-04-20 Shohei Enomoto , Takeharu Eda

We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, especially when training complex models on relatively small…

Machine Learning · Computer Science 2022-05-31 Christian Tomani , Daniel Cremers

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Hyekang Park , Jongyoun Noh , Youngmin Oh , Donghyeon Baek , Bumsub Ham

Imbalanced datasets pose a considerable challenge in training deep learning (DL) models for medical diagnostics, particularly for segmentation tasks. Imbalance may be associated with annotation quality limited annotated datasets, rare…

Image and Video Processing · Electrical Eng. & Systems 2025-04-08 Bashir Alam , Masa Cirkovic , Mete Harun Akcay , Md Kaf Shahrier , Sebastien Lafond , Hergys Rexha , Kurt Benke , Sepinoud Azimi , Janan Arslan

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Machine Learning · Computer Science 2025-02-03 Ouya Wang , Shenglong Zhou , Geoffrey Ye Li