paper-with-me

Papers

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

2019-08-22 · ICLR 2020 1 · Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). VL-BERT adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input. In it, each element of the input is either of a word from the input sentence, or a region-of-interest (RoI) from the input image. It is designed to fit for most of the visual-linguistic downstream tasks. To better exploit the generic representation, we pre-train VL-BERT on the massive-scale Conceptual Captions dataset, together with text-only corpus. Extensive empirical analysis demonstrates that the pre-training procedure can better align the visual-linguistic clues and benefit the downstream tasks, such as visual commonsense reasoning, visual question answering and referring expression comprehension. It is worth noting that VL-BERT achieved the first place of single model on the leaderboard of the VCR benchmark. Code is released at \url{https://github.com/jackroos/VL-BERT}.

📄 PDF Abstract BibTeX arXiv:1908.08530

Code (3)

jackroos/VL-BERT 공식 구현 pytorch
ImperialNLP/BertGen pytorch
jules-samaran/vl-bert pytorch

Tasks

Image-text matchingLanguage ModellingQuestion AnsweringReferring ExpressionReferring Expression ComprehensionSentenceVisual Commonsense ReasoningVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
VL-BERT VL-BERT is pre-trained on a large-scale image-captions dataset together with text-only corpus. The input to the model are either words from the input sentences or…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

TriBERT: Human-centric Audio-visual Representation Learning

2021-12-01 · NeurIPS 2021 12 · Tanzila Rahman, Mengyu Yang, Leonid Sigal

The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited …

Pose RetrievalRepresentation LearningRetrieval

TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation

2021-10-26 · Tanzila Rahman, Mengyu Yang, Leonid Sigal

The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited …

Pose RetrievalRepresentation LearningRetrieval

Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations

2020-09-10 · Meng-Jiun Chiou, Roger Zimmermann, Jiashi Feng

Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years. Inspired by human reasoning mechanisms, it is believed that e…

Objectobject-detectionObject DetectionRelational Reasoning+2

LIMIT-BERT : Linguistics Informed Multi-Task BERT

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Junru Zhou, Zhuosheng Zhang, Hai Zhao, Shuailiang Zhang

In this paper, we present Linguistics Informed Multi-Task BERT (LIMIT-BERT) for learning language representations across multiple linguistics tasks by Multi-Task Learning. LIMIT-BERT includes five key linguistics tasks: …

Language ModelingLanguage ModellingMulti-Task LearningPOS+2

Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance

2024-06-18 · Anna C. Marbut, John W. Chandler, Travis J. Wheeler

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 …

Benchmarking