paper-with-me

Papers

Uni-EDEN: Universal Encoder-Decoder Network by Multi-Granular Vision-Language Pre-training

2022-01-11 · Yehao Li, Jiahao Fan, Yingwei Pan, Ting Yao, Weiyao Lin, Tao Mei

Vision-language pre-training has been an emerging and fast-developing research topic, which transfers multi-modal knowledge from rich-resource pre-training task to limited-resource downstream tasks. Unlike existing works that predominantly learn a single generic encoder, we present a pre-trainable Universal Encoder-DEcoder Network (Uni-EDEN) to facilitate both vision-language perception (e.g., visual question answering) and generation (e.g., image captioning). Uni-EDEN is a two-stream Transformer based structure, consisting of three modules: object and sentence encoders that separately learns the representations of each modality, and sentence decoder that enables both multi-modal reasoning and sentence generation via inter-modal interaction. Considering that the linguistic representations of each image can span different granularities in this hierarchy including, from simple to comprehensive, individual label, a phrase, and a natural sentence, we pre-train Uni-EDEN through multi-granular vision-language proxy tasks: Masked Object Classification (MOC), Masked Region Phrase Generation (MRPG), Image-Sentence Matching (ISM), and Masked Sentence Generation (MSG). In this way, Uni-EDEN is endowed with the power of both multi-modal representation extraction and language modeling. Extensive experiments demonstrate the compelling generalizability of Uni-EDEN by fine-tuning it to four vision-language perception and generation downstream tasks.

📄 PDF Abstract BibTeX arXiv:2201.04026

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage CaptioningLanguage ModelingLanguage ModellingQuestion AnsweringSentenceVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text

2023-05-09 · Yova Kementchedjhieva, Ilias Chalkidis

Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we co…

ClassificationDecoderMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+4

Improved Multi-Stage Training of Online Attention-based Encoder-Decoder Models

2019-12-28 · Abhinav Garg, Dhananjaya Gowda, Ankur Kumar, Kwangyoun Kim 외

In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models. A three-stage training based on three levels of architectura…

DecoderLanguage ModelingLanguage ModellingMulti-Task Learning+1

GenEDA: Unleashing Generative Reasoning on Netlist via Multimodal Encoder-Decoder Aligned Foundation Model

2025-04-13 · Wenji Fang, Jing Wang, Yao Lu, Shang Liu 외

The success of foundation AI has motivated the research of circuit foundation models, which are customized to assist the integrated circuit (IC) design process. However, existing pre-trained circuit models are typically …

DecoderType prediction

Multilingual Neural Machine Translation With the Right Amount of Sharing

2022-06-01 · EAMT 2022 6 · Taido Purason, Andre Tättar

Large multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is t…

DecoderMachine TranslationNMTTranslation

Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders

2021-02-12 · Junwei Liao, Yu Shi, Ming Gong, Linjun Shou 외

Recently, universal neural machine translation (NMT) with shared encoder-decoder gained good performance on zero-shot translation. Unlike universal NMT, jointly trained language-specific encoders-decoders aim to achieve …

DecoderDenoisingMachine TranslationNMT+1