paper-with-me

Papers

Text-Only Training for Image Captioning using Noise-Injected CLIP

2022-11-01 · David Nukrai, Ron Mokady, Amir Globerson

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.

📄 PDF Abstract BibTeX arXiv:2211.00575

Code (4)

davidhuji/capdec 공식 구현 pytorch
avitej-iyer/CapDec-Recreation pytorch
uriberger/re_cap pytorch
zelaki/wsac pytorch

Tasks

DecoderImage CaptioningLanguage ModellingSemi Supervised Learning for Image Captioning

Methods 이 논문이 사용한 방법론

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
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…
Adam 설명 없음
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…

Similar Papers 제목 키워드 기반

Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning

2022-12-27 · ICCV 2023 1 · Wooyoung Kang, Jonghwan Mun, Sungjun Lee, Byungseok Roh

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 RetrievalRetrieval

NLIP: Noise-robust Language-Image Pre-training

2022-12-14 · Runhui Huang, Yanxin Long, Jianhua Han, Hang Xu 외

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+3

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

2024-01-04 · Longtian Qiu, Shan Ning, Xuming He

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

2019-11-01 · WS 2019 11 · Dalin Wang, Daniel Beck, Trevor Cohn

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 Captioning

IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning

2024-09-26 · Soeun Lee, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim

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