Text-Only Training for Image Captioning using Noise-Injected CLIP
We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images. Our approach relies on the fact that CLIP is trained to make visual and textual embeddings similar. Therefore, we only need to learn how to translate CLIP textual embeddings back into text, and we can learn how to do this by learning a decoder for the frozen CLIP text encoder using only text. We argue that this intuition is "almost correct" because of a gap between the embedding spaces, and propose to rectify this via noise injection during training. We demonstrate the effectiveness of our approach by showing SOTA zero-shot image captioning across four benchmarks, including style transfer. Code, data, and models are available on GitHub.
Code (4)
Tasks
DecoderImage CaptioningLanguage ModellingSemi Supervised Learning for Image CaptioningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning
Image captioning is one of the straightforward tasks that can take advantage of large-scale web-crawled data which provides rich knowledge about the visual world for a captioning model. However, since web-crawled data co…
Image CaptioningImage RetrievalRetrievalNLIP: Noise-robust Language-Image Pre-training
Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly r…
Image CaptioningImage-text RetrievalMemorizationRetrieval+3Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training
Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastiv…
DescriptiveImage CaptioningRerankingVisual Question Answering (VQA)On the Role of Scene Graphs in Image Captioning
Scene graphs represent semantic information in images, which can help image captioning system to produce more descriptive outputs versus using only the image as context. Recent captioning approaches rely on ad-hoc approa…
DescriptiveImage CaptioningIFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between…
Image CaptioningRetrievalVideo Captioning