English
Related papers

Related papers: POS-BERT: Point Cloud One-Stage BERT Pre-Training

200 papers

Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training…

Computation and Language · Computer Science 2023-01-06 Luke Gessler , Amir Zeldes

Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Qibo Qiu , Honghui Yang , Wenxiao Wang , Shun Zhang , Haiming Gao , Haochao Ying , Wei Hua , Xiaofei He

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-24 Dongwei Jiang , Wubo Li , Ruixiong Zhang , Miao Cao , Ne Luo , Yang Han , Wei Zou , Xiangang Li

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency…

Computation and Language · Computer Science 2023-01-02 Maren Pielka , Svetlana Schmidt , Lisa Pucknat , Rafet Sifa

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

Computation and Language · Computer Science 2022-09-28 Arnav Ladkat , Aamir Miyajiwala , Samiksha Jagadale , Rekha Kulkarni , Raviraj Joshi

Point cloud video perception has become an essential task for the realm of 3D vision. Current 4D representation learning techniques typically engage in iterative processing coupled with dense query operations. Although effective in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Jie Wang , Tingfa Xu , Lihe Ding , Xinjie Zhang , Long Bai , Jianan Li

Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and its consecutive variants have been proposed to further improve the performance of the pre-trained language models.…

Computation and Language · Computer Science 2021-11-29 Yiming Cui , Wanxiang Che , Ting Liu , Bing Qin , Ziqing Yang

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

Machine Learning · Computer Science 2019-12-23 Xiaocong Du , Gouranga Charan , Frank Liu , Yu Cao

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense…

Computation and Language · Computer Science 2023-06-21 Kun Zhou , Xiao Liu , Yeyun Gong , Wayne Xin Zhao , Daxin Jiang , Nan Duan , Ji-Rong Wen

Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Cheng Zeng , Xiatian Qi , Chi Chen , Kai Sun , Wangle Zhang , Yuxuan Liu , Yan Meng , Bisheng Yang

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Qiong Wu , Shubin Huang , Yiyi Zhou , Pingyang Dai , Annan Shu , Guannan Jiang , Rongrong Ji

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Zhongbin Fang , Xiangtai Li , Xia Li , Joachim M. Buhmann , Chen Change Loy , Mengyuan Liu

This paper aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. Many such modelling architectures and methods to train those architectures have been proposed,…

Computation and Language · Computer Science 2023-05-10 Kris Cao

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Andrej Janda , Brandon Wagstaff , Edwin G. Ng , Jonathan Kelly

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Canyu Zhang , Zhenyao Wu , Xinyi Wu , Ziyu Zhao , Song Wang

This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between…

Computation and Language · Computer Science 2021-06-08 Ye Jia , Heiga Zen , Jonathan Shen , Yu Zhang , Yonghui Wu

The current era of natural language processing (NLP) has been defined by the prominence of pre-trained language models since the advent of BERT. A feature of BERT and models with similar architecture is the objective of masked language…

Computation and Language · Computer Science 2023-07-04 Ed S. Ma

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Transformer based architectures have become de-facto models used for a range of Natural Language Processing tasks. In particular, the BERT based models achieved significant accuracy gain for GLUE tasks, CoNLL-03 and SQuAD. However, BERT…

Computation and Language · Computer Science 2021-04-21 Sheng Shen , Zhen Dong , Jiayu Ye , Linjian Ma , Zhewei Yao , Amir Gholami , Michael W. Mahoney , Kurt Keutzer