paper-with-me

홈 › Papers

An Empirical Study of Training End-to-End Vision-and-Language Transformers

2021-11-03 · CVPR 2022 1 · Zi-Yi Dou, Yichong Xu, Zhe Gan, JianFeng Wang, Shuohang Wang, Lijuan Wang, Chenguang Zhu, Pengchuan Zhang, Lu Yuan, Nanyun Peng, Zicheng Liu, Michael Zeng

Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be more efficient than previous region-feature-based methods, their performance on downstream tasks often degrades significantly. In this paper, we present METER, a Multimodal End-to-end TransformER framework, through which we investigate how to design and pre-train a fully transformer-based VL model in an end-to-end manner. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion module (e.g., merged attention vs. co-attention), architectural design (e.g., encoder-only vs. encoder-decoder), and pre-training objectives (e.g., masked image modeling). We conduct comprehensive experiments and provide insights on how to train a performant VL transformer. METER achieves an accuracy of 77.64% on the VQAv2 test-std set using only 4M images for pre-training, surpassing the state-of-the-art region-feature-based model by 1.04%, and outperforming the previous best fully transformer-based model by 1.6%. Notably, when further scaled up, our best VQA model achieves an accuracy of 80.54%. Code and pre-trained models are released at https://github.com/zdou0830/METER.

📄 PDF Abstract BibTeX arXiv:2111.02387

Code (3)

zdou0830/meter 공식 구현 pytorch
claws-lab/multimodal-robustness-xmai pytorch
iflytek/vle pytorch

Tasks

Cross-Modal RetrievalDecoderVisual Question Answering (VQA)Visual Reasoning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
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…

Similar Papers 제목 키워드 기반

Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR

2024-05-27 · Zhenyang Li, Yangyang Guo, Kejie Wang, Xiaolin Chen 외

Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question answering over visual scenes. To achieve this goal, a model is required to provide an acceptable rationale as the reason for the predicte…

Question AnsweringTAGVisual Commonsense ReasoningVisual Reasoning

MLP Architectures for Vision-and-Language Modeling: An Empirical Study

2021-12-08 · Yixin Nie, Linjie Li, Zhe Gan, Shuohang Wang 외

We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, …

Language ModelingLanguage ModellingVisual Question Answering (VQA)

Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels

2024-01-23 · Seungho Lee, Seoungyoon Kang, Hyunjung Shim

This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweight segmentation head, our approach effect…

Language ModelingLanguage ModellingSegmentationSemantic Segmentation

Parameter-efficient Model Adaptation for Vision Transformers

2022-03-29 · Xuehai He, Chunyuan Li, Pengchuan Zhang, Jianwei Yang 외

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either upd…

BenchmarkingClassificationimage-classificationImage Classification+2

An Empirical Study Of Self-supervised Learning Approaches For Object Detection With Transformers

2022-05-11 · Gokul Karthik Kumar, Sahal Shaji Mullappilly, Abhishek Singh Gehlot

Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research ad…

image-classificationImage ClassificationImage ReconstructionLanguage Modeling+6