paper-with-me

Papers

Retrieval-augmented Image Captioning

2023-02-16 · Rita Ramos, Desmond Elliott, Bruno Martins

Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.

📄 PDF Abstract BibTeX arXiv:2302.08268

Code (1)

ritaramo/extra 공식 구현 pytorch

Tasks

DecoderImage CaptioningRetrievalText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Adam 설명 없음
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
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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 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…

Similar Papers 제목 키워드 기반

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning

2025-09-19 · Xiaosheng Long, Hanyu Wang, Zhentao Song, Kun Luo 외 arxiv

Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) …

Image Captioning

Towards Retrieval-Augmented Architectures for Image Captioning

2024-05-21 · Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi 외

The objective of image captioning models is to bridge the gap between the visual and linguistic modalities by generating natural language descriptions that accurately reflect the content of input images. In recent years,…

Image CaptioningLanguage ModelingLanguage ModellingRetrieval

Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning

2024-06-04 · Wenyan Li, Jiaang Li, Rita Ramos, Raphael Tang 외

Recent advances in retrieval-augmented models for image captioning highlight the benefit of retrieving related captions for efficient, lightweight models with strong domain-transfer capabilities. While these models demon…

Image CaptioningRetrieval

CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning

2025-07-27 · George Ibrahim, Rita Ramos, Yova Kementchedjhieva arxiv

Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameter…

Image Captioning

TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules

2025-02-16 · Ruoyu Zhang, Lulu Wang, Yi He, Tongling Pan 외

Recent advancements in large language models (LLMs) have significantly enhanced the fluency and logical coherence of image captioning. Retrieval-Augmented Generation (RAG) is widely adopted to incorporate external knowle…

GPUImage CaptioningRAGRetrieval+1