E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
원문 초록
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline. In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VDDT: Improving Vessel Detection with Deformable Transfomer
Global Object Proposals for Improving Multi-Sentence Video Descriptions
Universal Fine-grained Visual Categorization by Concept Guided Learning
Integrity Assessment of Maritime Object Detection Impacted by Partial Camera Obstruction
Ensemble Fusion for Small Object Detection
Small Object Detection for Birds with Swin Transformer
토론
이 논문과 연결된 포럼 글이 아직 없습니다.