Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance across several tasks. Such models excel at object-centric recognition yet learn text representations that seem invariant to word order, failing to compose known concepts in novel ways. However, no evidence exists that any VLM, including large-scale single-stream models such as GPT-4V, identifies compositions successfully. In this paper, we introduce a framework to significantly improve the ability of existing models to encode compositional language, with over 10% absolute improvement on compositionality benchmarks, while maintaining or improving the performance on standard object-recognition and retrieval benchmarks. Our code and pre-trained models are publicly available at https://github.com/netflix/clove.

翻译：近年来，视觉与语言任务的性能显著提升。基础视觉-语言模型（如CLIP）已在多种场景中得到应用，并在多项任务中展现出卓越性能。此类模型擅长以对象为中心的识别，但学习到的文本表征似乎对词序不变，无法以新颖方式组合已知概念。然而，尚无证据表明任何视觉-语言模型（包括GPT-4V等大规模单流模型）能够成功识别组合。在本文中，我们提出一种框架，显著提升现有模型编码组合语言的能力，在组合性基准测试上实现超过10%的绝对改进，同时保持或提升标准对象识别与检索基准的性能。我们的代码和预训练模型已在 https://github.com/netflix/clove 公开提供。