English
Related papers

Related papers: BEiT: BERT Pre-Training of Image Transformers

200 papers

We apply a Transformer architecture, specifically BERT, to learn flexible and high quality molecular representations for drug discovery problems. We study the impact of using different combinations of self-supervised tasks for pre-training,…

Machine Learning · Computer Science 2020-11-30 Benedek Fabian , Thomas Edlich , Héléna Gaspar , Marwin Segler , Joshua Meyers , Marco Fiscato , Mohamed Ahmed

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Pengfei Gu , Huimin Li , Yejia Zhang , Chaoli Wang , Danny Z. Chen

Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Joel Valdivia Ortega , Tingying Peng , Marion Jasnin

Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xin Li , Peng Li , Zeyong Wei , Zhe Zhu , Mingqiang Wei , Junhui Hou , Liangliang Nan , Jing Qin , Haoran Xie , Fu Lee Wang

In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which…

Computation and Language · Computer Science 2021-11-05 Tan Huang

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs),…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Ke Yang , Sixian Wang , Jincheng Dai , Kailin Tan , Kai Niu , Ping Zhang

Synthesizing medical images, such as PET, is a challenging task due to the fact that the intensity range is much wider and denser than those in photographs and digital renderings and are often heavily biased toward zero. Above all,…

We explore the performance of Bidirectional Encoder Representations from Transformers (BERT) at definition extraction. We further propose a joint model of BERT and Text Level Graph Convolutional Network so as to incorporate dependencies…

Computation and Language · Computer Science 2020-09-18 Aadarsh Singh , Priyanshu Kumar , Aman Sinha

This paper shows that self-supervised visual pre-training from real-world images is effective for learning motor control tasks from pixels. We first train the visual representations by masked modeling of natural images. We then freeze the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Tete Xiao , Ilija Radosavovic , Trevor Darrell , Jitendra Malik

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Jihao Liu , Jinliang Zheng , Boxiao Liu , Yu Liu , Hongsheng Li

Learning Bird's Eye View (BEV) representation from surrounding-view cameras is of great importance for autonomous driving. In this work, we propose a Geometry-guided Kernel Transformer (GKT), a novel 2D-to-BEV representation learning…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Shaoyu Chen , Tianheng Cheng , Xinggang Wang , Wenming Meng , Qian Zhang , Wenyu Liu

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To…

Computation and Language · Computer Science 2021-09-17 Liang Ding , Di Wu , Dacheng Tao

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for…

Computation and Language · Computer Science 2022-03-15 Yiming Cui , Ziqing Yang , Ting Liu

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of…

Computation and Language · Computer Science 2023-06-13 Jeremy Gwinnup , Kevin Duh

In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Adithya Giri

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yao Qiang , Chengyin Li , Prashant Khanduri , Dongxiao Zhu

In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources and most of the models are trained from…

Computation and Language · Computer Science 2021-10-15 Cheng Chen , Yichun Yin , Lifeng Shang , Xin Jiang , Yujia Qin , Fengyu Wang , Zhi Wang , Xiao Chen , Zhiyuan Liu , Qun Liu

We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of exfiltration at low false positive rates. While previous work mostly examines fine-tuned…

Cryptography and Security · Computer Science 2026-04-14 Miloš Tomić , Aleksa Cvetanović , Predrag Tadić