LIVIVO - Search results -

Search results

Result 1 - 10 of total 12

Book ; Online: VL-BEiT

Bao, Hangbo / Wang, Wenhui / Dong, Li / Wei, Furu

Generative Vision-Language Pretraining

2022

Abstract: We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared ... ...

Abstract	We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental results show that VL-BEiT obtains strong results on various vision-language benchmarks, such as visual question answering, visual reasoning, and image-text retrieval. Moreover, our method learns transferable visual features, achieving competitive performance on image classification, and semantic segmentation.
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Computation and Language
Publishing date	2022-06-02
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Corrupted Image Modeling for Self-Supervised Visual Pre-Training

Fang, Yuxin / Dong, Li / Bao, Hangbo / Wang, Xinggang / Wei, Furu

2022

Abstract: We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are randomly ... ...

Abstract	We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are randomly selected and replaced with plausible alternatives sampled from the BEiT output distribution. Given this corrupted image, an enhancer network learns to either recover all the original image pixels, or predict whether each visual token is replaced by a generator sample or not. The generator and the enhancer are simultaneously trained and synergistically updated. After pre-training, the enhancer can be used as a high-capacity visual encoder for downstream tasks. CIM is a general and flexible visual pre-training framework that is suitable for various network architectures. For the first time, CIM demonstrates that both ViT and CNN can learn rich visual representations using a unified, non-Siamese framework. Experimental results show that our approach achieves compelling results in vision benchmarks, such as ImageNet classification and ADE20K semantic segmentation. Comment: ICLR 2023
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning
Subject code	006
Publishing date	2022-02-07
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Attention Temperature Matters in Abstractive Summarization Distillation

Zhang, Shengqiang / Zhang, Xingxing / Bao, Hangbo / Wei, Furu

2021

Abstract: Recent progress of abstractive text summarization largely relies on large pre-trained sequence-to-sequence Transformer models, which are computationally expensive. This paper aims to distill these large models into smaller ones for faster inference and ... ...

Abstract	Recent progress of abstractive text summarization largely relies on large pre-trained sequence-to-sequence Transformer models, which are computationally expensive. This paper aims to distill these large models into smaller ones for faster inference and minimal performance loss. Pseudo-labeling based methods are popular in sequence-to-sequence model distillation. In this paper, we find simply manipulating attention temperatures in Transformers can make pseudo labels easier to learn for student models. Our experiments on three summarization datasets show our proposed method consistently improves over vanilla pseudo-labeling based methods. We also find that both the pseudo labels and summaries produced by our students are shorter and more abstractive. Our code is available at \url{https://github.com/Shengqiang-Zhang/plate}. Comment: Accepted in ACL 2022 Main conference
Keywords	Computer Science - Computation and Language
Publishing date	2021-06-07
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: BEiT

Bao, Hangbo / Dong, Li / Wei, Furu

BERT Pre-Training of Image Transformers

2021

Abstract: We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to ... ...

Abstract	We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit. Comment: A Path to the BERT Moment of CV. Work in progress
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
Subject code	006
Publishing date	2021-06-15
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: BEiT v2

Peng, Zhiliang / Dong, Li / Bao, Hangbo / Ye, Qixiang / Wei, Furu

Masked Image Modeling with Vector-Quantized Visual Tokenizers

2022

Abstract: Masked image modeling (MIM) has demonstrated impressive results in self-supervised representation learning by recovering corrupted image patches. However, most methods still operate on low-level image pixels, which hinders the exploitation of high-level ... ...

Abstract	Masked image modeling (MIM) has demonstrated impressive results in self-supervised representation learning by recovering corrupted image patches. However, most methods still operate on low-level image pixels, which hinders the exploitation of high-level semantics for representation models. In this study, we propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction, providing a systematic way to promote MIM from pixel-level to semantic-level. Specifically, we introduce vector-quantized knowledge distillation to train the tokenizer, which discretizes a continuous semantic space to compact codes. We then pretrain vision Transformers by predicting the original visual tokens for the masked image patches. Moreover, we encourage the model to explicitly aggregate patch information into a global image representation, which facilities linear probing. Experiments on image classification and semantic segmentation show that our approach outperforms all compared MIM methods. On ImageNet-1K (224 size), the base-size BEiT v2 achieves 85.5% top-1 accuracy for fine-tuning and 80.1% top-1 accuracy for linear probing. The large-size BEiT v2 obtains 87.3% top-1 accuracy for ImageNet-1K (224 size) fine-tuning, and 56.7% mIoU on ADE20K for semantic segmentation. The code and pretrained models are available at https://aka.ms/beit.
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2022-08-12
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: s2s-ft

Bao, Hangbo / Dong, Li / Wang, Wenhui / Yang, Nan / Wei, Furu

Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning

2021

Abstract: Pretrained bidirectional Transformers, such as BERT, have achieved significant improvements in a wide variety of language understanding tasks, while it is not straightforward to directly apply them for natural language generation. In this paper, we ... ...

Abstract	Pretrained bidirectional Transformers, such as BERT, have achieved significant improvements in a wide variety of language understanding tasks, while it is not straightforward to directly apply them for natural language generation. In this paper, we present a sequence-to-sequence fine-tuning toolkit s2s-ft, which adopts pretrained Transformers for conditional generation tasks. Inspired by UniLM, we implement three sequence-to-sequence fine-tuning algorithms, namely, causal fine-tuning, masked fine-tuning, and pseudo-masked fine-tuning. By leveraging the existing pretrained bidirectional Transformers, experimental results show that s2s-ft achieves strong performance on several benchmarks of abstractive summarization, and question generation. Moreover, we demonstrate that the package s2s-ft supports both monolingual and multilingual NLG tasks. The s2s-ft toolkit is available at https://github.com/microsoft/unilm/tree/master/s2s-ft. Comment: Demo paper for the s2s-ft toolkit: https://github.com/microsoft/unilm/tree/master/s2s-ft
Keywords	Computer Science - Computation and Language
Subject code	004
Publishing date	2021-10-26
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: MiniLMv2

Wang, Wenhui / Bao, Hangbo / Huang, Shaohan / Dong, Li / Wei, Furu

Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers

2020

Abstract: We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention relations as ... ...

Abstract	We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention relations as scaled dot-product between the pairs of query, key, and value vectors within each self-attention module. Then we employ the above relational knowledge to train the student model. Besides its simplicity and unified principle, more favorably, there is no restriction in terms of the number of student's attention heads, while most previous work has to guarantee the same head number between teacher and student. Moreover, the fine-grained self-attention relations tend to fully exploit the interaction knowledge learned by Transformer. In addition, we thoroughly examine the layer selection strategy for teacher models, rather than just relying on the last layer as in MiniLM. Experimental results demonstrate that our models distilled from base-size and large-size teachers (BERT, and RoBERTa) outperform the state of the art.
Keywords	Computer Science - Computation and Language
Publishing date	2020-12-31
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: THE-X

Chen, Tianyu / Bao, Hangbo / Huang, Shaohan / Dong, Li / Jiao, Binxing / Jiang, Daxin / Zhou, Haoyi / Li, Jianxin / Wei, Furu

Privacy-Preserving Transformer Inference with Homomorphic Encryption

2022

Abstract: As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e.g., search history, medical record, bank account). Privacy-preserving inference of transformer ... ...

Abstract	As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e.g., search history, medical record, bank account). Privacy-preserving inference of transformer models is on the demand of cloud service users. To protect privacy, it is an attractive choice to compute only with ciphertext in homomorphic encryption (HE). However, enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks, which are not supported by current HE tools yet. In this work, we introduce $\textit{THE-X}$, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models developed by popular frameworks. $\textit{THE-X}$ proposes a workflow to deal with complex computation in transformer networks, including all the non-polynomial functions like GELU, softmax, and LayerNorm. Experiments reveal our proposed $\textit{THE-X}$ can enable transformer inference on encrypted data for different downstream tasks, all with negligible performance drop but enjoying the theory-guaranteed privacy-preserving advantage. Comment: Findings of ACL 2022
Keywords	Computer Science - Cryptography and Security ; Computer Science - Computation and Language
Subject code	330
Publishing date	2022-05-31
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: MiniLM

Wang, Wenhui / Wei, Furu / Dong, Li / Bao, Hangbo / Yang, Nan / Zhou, Ming

Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

2020

Abstract: Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges for fine- ... ...

Abstract	Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and online serving in real-life applications due to latency and capacity constraints. In this work, we present a simple and effective approach to compress large Transformer (Vaswani et al., 2017) based pre-trained models, termed as deep self-attention distillation. The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher). Specifically, we propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Furthermore, we introduce the scaled dot-product between values in the self-attention module as the new deep self-attention knowledge, in addition to the attention distributions (i.e., the scaled dot-product of queries and keys) that have been used in existing works. Moreover, we show that introducing a teacher assistant (Mirzadeh et al., 2019) also helps the distillation of large pre-trained Transformer models. Experimental results demonstrate that our monolingual model outperforms state-of-the-art baselines in different parameter size of student models. In particular, it retains more than 99% accuracy on SQuAD 2.0 and several GLUE benchmark tasks using 50% of the Transformer parameters and computations of the teacher model. We also obtain competitive results in applying deep self-attention distillation to multilingual pre-trained models. Comment: Code and models: https://github.com/microsoft/unilm/tree/master/minilm
Keywords	Computer Science - Computation and Language
Publishing date	2020-02-25
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: VLMo

Bao, Hangbo / Wang, Wenhui / Dong, Li / Liu, Qiang / Mohammed, Owais Khan / Aggarwal, Kriti / Som, Subhojit / Wei, Furu

Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

2021

Abstract: We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains ... ...

Abstract	We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA, NLVR2 and image-text retrieval. The code and pretrained models are available at https://aka.ms/vlmo. Comment: Work in progress
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Computation and Language ; Computer Science - Machine Learning
Subject code	004
Publishing date	2021-11-03
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

Your last searches

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED