English
Related papers

Related papers: Improving Neural Network Quantization without Retr…

200 papers

Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and…

Machine Learning · Computer Science 2024-02-27 Wenyu Jiang , Hao Cheng , Mingcai Chen , Chongjun Wang , Hongxin Wei

Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on…

Machine Learning · Computer Science 2023-02-22 Xiuying Wei , Yunchen Zhang , Xiangguo Zhang , Ruihao Gong , Shanghang Zhang , Qi Zhang , Fengwei Yu , Xianglong Liu

Deep neural networks for image classification often exhibit overconfidence on out-of-distribution (OOD) samples. To address this, we introduce Geometrically Constrained Outlier Synthesis (GCOS), a training-time regularization framework…

Machine Learning · Computer Science 2026-05-27 Daniil Karzanov , Marcin Detyniecki

As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However,…

Machine Learning · Computer Science 2026-03-06 Roussel Desmond Nzoyem

Graph neural networks (GNNs) have achieved impressive performance when testing and training graph data come from identical distribution. However, existing GNNs lack out-of-distribution generalization abilities so that their performance…

Machine Learning · Computer Science 2021-12-15 Haoyang Li , Xin Wang , Ziwei Zhang , Wenwu Zhu

Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that…

Machine Learning · Computer Science 2025-06-04 Guillaume Godin

Deep neural networks have demonstrated great generalization capabilities for tasks whose training and test sets are drawn from the same distribution. Nevertheless, out-of-distribution (OOD) detection remains a challenging task that has…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Brian K. S. Isaac-Medina , Toby P. Breckon

Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However, out-of-distribution generalization for regression-the…

Machine Learning · Computer Science 2024-01-01 Benjamin Eyre , Elliot Creager , David Madras , Vardan Papyan , Richard Zemel

Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision weights and activations involves a demanding optimization task, which calls for…

Machine Learning · Computer Science 2021-05-25 Ziang Long , Penghang Yin , Jack Xin

Optical neural networks (ONNs) have demonstrated record-breaking potential in high-performance neuromorphic computing due to their ultra-high execution speed and low energy consumption. However, current learning protocols fail to provide…

Emerging Technologies · Computer Science 2021-09-07 Jiaqi Gu , Chenghao Feng , Zheng Zhao , Zhoufeng Ying , Ray T. Chen , David Z. Pan

Deep neural networks have achieved significant success in the last decades, but they are not well-calibrated and often produce unreliable predictions. A large number of literature relies on uncertainty quantification to evaluate the…

Machine Learning · Computer Science 2023-11-13 Russell Alan Hart , Linlin Yu , Yifei Lou , Feng Chen

Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Dawei Yang , Ning He , Xing Hu , Zhihang Yuan , Jiangyong Yu , Chen Xu , Zhe Jiang

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimator (STE) to train…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Junghyup Lee , Dohyung Kim , Bumsub Ham

Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on…

Computer Vision and Pattern Recognition · Computer Science 2018-10-05 Julien Girard , Youssef Tamaazousti , Hervé Le Borgne , Céline Hudelot

Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Deep Neural networks (DNNs) tend to generate over-confident predictions when presented with inputs that are significantly…

Machine Learning · Computer Science 2022-02-24 Sumedh A Sontakke , Buvaneswari Ramanan , Laurent Itti , Thomas Woo

Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and…

Machine Learning · Computer Science 2026-04-10 Binxing Xu , Hao Gu , Lujun Li , Hao Wang , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Xintong Yang , Chao Li , Sirui Han , Yike Guo

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may…

Machine Learning · Computer Science 2026-05-15 Yuxin Guo , Yihao Yue , Yunhao Ni , Yizhou Ruan , Jie Luo , Wenjun Wu , Lei Huang

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for…

Machine Learning · Computer Science 2023-01-26 Matteo Risso , Alessio Burrello , Luca Benini , Enrico Macii , Massimo Poncino , Daniele Jahier Pagliari

Convolutional neural networks require significant memory bandwidth and storage for intermediate computations, apart from substantial computing resources. Neural network quantization has significant benefits in reducing the amount of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-30 Ron Banner , Yury Nahshan , Elad Hoffer , Daniel Soudry

A major challenge in machine learning is resilience to out-of-distribution data, that is data that exists outside of the distribution of a model's training data. Training is often performed using limited, carefully curated datasets and so…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Christopher J. Holder , Majid Khonji , Jorge Dias , Muhammad Shafique