paper-with-me

홈 › Papers

ViTOC: Vision Transformer and Object-aware Captioner

2024-11-09 · Feiyang Huang

This paper presents ViTOC (Vision Transformer and Object-aware Captioner), a novel vision-language model for image captioning that addresses the challenges of accuracy and diversity in generated descriptions. Unlike conventional approaches, ViTOC employs a dual-path architecture based on Vision Transformer and object detector, effectively fusing global visual features and local object information through learnable vectors. The model introduces an innovative object-aware prompting strategy that significantly enhances its capability in handling long-tail data. Experiments on the standard COCO dataset demonstrate that ViTOC outperforms baseline models across all evaluation metrics. Additionally, we propose a reference-free evaluation method based on CLIP to further validate the model's effectiveness. By utilizing pretrained visual model parameters, ViTOC achieves efficient end-to-end training.

📄 PDF Abstract BibTeX arXiv:2411.07265

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityImage CaptioningLanguage ModelingLanguage ModellingObject

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

LocCa: Visual Pretraining with Location-aware Captioners

2024-03-28 · Bo Wan, Michael Tschannen, Yongqin Xian, Filip Pavetic 외

Image captioning has been shown as an effective pretraining method similar to contrastive pretraining. However, the incorporation of location-aware information into visual pretraining remains an area with limited researc…

DecoderImage Captioning

ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions

2023-03-12 · Deyao Zhu, Jun Chen, Kilichbek Haydarov, Xiaoqian Shen 외

Asking insightful questions is crucial for acquiring knowledge and expanding our understanding of the world. However, the importance of questioning has been largely overlooked in AI research, where models have been prima…

Image CaptioningQuestion AnsweringVisual Reasoning

More Grounded Image Captioning by Distilling Image-Text Matching Model

2020-04-01 · CVPR 2020 6 · Yuanen Zhou, Meng Wang, Daqing Liu, Zhenzhen Hu 외

Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a c…

Image CaptioningImage-text matchingKnowledge DistillationPOS+2

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

2023-11-27 · Chenglin Yang, Siyuan Qiao, Yuan Cao, Yu Zhang 외

Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and d…

Caption GenerationImage-text RetrievalLanguage ModellingText Retrieval+2

OSIC: A New One-Stage Image Captioner Coined

2022-11-04 · Bo wang, Zhao Zhang, Mingbo Zhao, Xiaojie Jin 외

Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operatio…

DescriptiveLanguage ModellingObjectText Generation