Grid-VLP: Revisiting Grid Features for Vision-Language Pre-training
원문 초록
Existing approaches to vision-language pre-training (VLP) heavily rely on an object detector based on bounding boxes (regions), where salient objects are first detected from images and then a Transformer-based model is used for cross-modal fusion. Despite their superior performance, these approaches are bounded by the capability of the object detector in terms of both effectiveness and efficiency. Besides, the presence of object detection imposes unnecessary constraints on model designs and makes it difficult to support end-to-end training. In this paper, we revisit grid-based convolutional features for vision-language pre-training, skipping the expensive region-related steps. We propose a simple yet effective grid-based VLP method that works surprisingly well with the grid features. By pre-training only with in-domain datasets, the proposed Grid-VLP method can outperform most competitive region-based VLP methods on three examined vision-language understanding tasks. We hope that our findings help to further advance the state of the art of vision-language pre-training, and provide a new direction towards effective and efficient VLP.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
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
Domain Generalized Object Detection for Remote Sensing Images
Context-Aware Block Net for Small Object Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.