nocaps: novel object captioning at scale

Abstract

Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale benchmark for this task. Dubbed 'nocaps', for novel object captioning at scale, our benchmark consists of 166,100 human-generated captions describing 15,100 images from the OpenImages validation and test sets. The associated training data consists of COCO image-caption pairs, plus OpenImages image-level labels and object bounding boxes. Since OpenImages contains many more classes than COCO, nearly 400 object classes seen in test images have no or very few associated training captions (hence, nocaps). We extend existing novel object captioning models to establish strong baselines for this benchmark and provide analysis to guide future work on this task.

References in corpus (2)

• Improved Image Captioning via Policy Gradient optimization of SPIDEr
• Decoupled Novel Object Captioner

Cited by in corpus (10)

• A Survey on Multimodal Large Language Models
• VLP: A Survey on Vision-Language Pre-training
• Deep Learning Approaches on Image Captioning: A Review
• WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research
• Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
• A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
• Situating the social issues of image generation models in the model life cycle: a sociotechnical approach
• Learning to Select: A Fully Attentive Approach for Novel Object Captioning
• ProCap: Projection-Aware Captioning for Spatial Augmented Reality
• Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction