English
Related papers

Related papers: SuperShaper: Task-Agnostic Super Pre-training of B…

200 papers

As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target…

Machine Learning · Computer Science 2023-10-17 Yun Yi , Haokui Zhang , Rong Xiao , Nannan Wang , Xiaoyu Wang

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

Computation and Language · Computer Science 2024-06-19 Anna C. Marbut , John W. Chandler , Travis J. Wheeler

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of…

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves…

Computer Vision and Pattern Recognition · Computer Science 2021-04-15 Dilin Wang , Meng Li , Chengyue Gong , Vikas Chandra

Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly optimizing the model weight and architecture parameters in a…

Machine Learning · Computer Science 2021-08-11 Ruochen Wang , Minhao Cheng , Xiangning Chen , Xiaocheng Tang , Cho-Jui Hsieh

The highly popular Transformer architecture, based on self-attention, is the foundation of large pretrained models such as BERT, that have become an enduring paradigm in NLP. While powerful, the computational resources and time required to…

Computation and Language · Computer Science 2021-08-31 Ran Tian , Joshua Maynez , Ankur P. Parikh

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

Computation and Language · Computer Science 2020-04-14 Shangwen Lv , Yuechen Wang , Daya Guo , Duyu Tang , Nan Duan , Fuqing Zhu , Ming Gong , Linjun Shou , Ryan Ma , Daxin Jiang , Guihong Cao , Ming Zhou , Songlin Hu

Detecting anomalies in musculoskeletal radiographs is of paramount importance for large-scale screening in the radiology workflow. Supervised deep networks take for granted a large number of annotations by radiologists, which is often…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Antoine Spahr , Behzad Bozorgtabar , Jean-Philippe Thiran

There have been recent efforts to learn more meaningful representations via fixed length codewords from mesh data, since a mesh serves as a complete model of underlying 3D shape compared to a point cloud. However, the mesh connectivity…

Computer Vision and Pattern Recognition · Computer Science 2023-08-30 Eric Lei , Muhammad Asad Lodhi , Jiahao Pang , Junghyun Ahn , Dong Tian

Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains. Recently, pre-training a large-scale language model has become a promising direction for coping with the…

Computation and Language · Computer Science 2021-12-02 Zihan Liu , Feijun Jiang , Yuxiang Hu , Chen Shi , Pascale Fung

Neural Architecture Search (NAS) has been used recently to achieve improved performance in various tasks and most prominently in image classification. Yet, current search strategies rely on large labeled datasets, which limit their usage in…

Machine Learning · Computer Science 2020-07-06 Sapir Kaplan , Raja Giryes

Neural parameter allocation search (NPAS) automates parameter sharing by obtaining weights for a network given an arbitrary, fixed parameter budget. Prior work has two major drawbacks we aim to address. First, there is a disconnect in the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Piotr Teterwak , Soren Nelson , Nikoli Dryden , Dina Bashkirova , Kate Saenko , Bryan A. Plummer

In self-supervised learning, a model is trained to solve a pretext task, using a data set whose annotations are created by a machine. The objective is to transfer the trained weights to perform a downstream task in the target domain. We…

Machine Learning · Computer Science 2021-10-22 Prathamesh Sonawane , Sparsh Drolia , Saqib Shamsi , Bhargav Jain

We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have…

Machine Learning · Computer Science 2020-08-11 Shikun Liu , Zhe Lin , Yilin Wang , Jianming Zhang , Federico Perazzi , Edward Johns

It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…

Machine Learning · Computer Science 2022-03-16 A. Tuan Nguyen , Ser Nam Lim , Philip Torr

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the…

Computation and Language · Computer Science 2022-02-03 Junxian He , Chunting Zhou , Xuezhe Ma , Taylor Berg-Kirkpatrick , Graham Neubig

Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Fulong Ma , Guoyang Zhao , Weiqing Qi , Ming Liu , Jun Ma
‹ Prev 1 3 4 5 6 7 10 Next ›