Related papers: Self-critical Sequence Training for Image Captioni…
Recent image captioning models are achieving impressive results based on popular metrics, i.e., BLEU, CIDEr, and SPICE. However, focusing on the most popular metrics that only consider the overlap between the generated captions and human…
We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality…
Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in deep neural networks have substantially improved the performance…
When describing images with natural language, the descriptions can be made more informative if tuned using downstream tasks. This is often achieved by training two networks: a "speaker network" that generates sentences given an image, and a…
Recent multi-modal large language models (MLLMs) often struggle to generate personalized image captions, even when trained on high-quality captions. In this work, we observe that such limitations persist in existing post-training-based MLLM…
Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we…
Generating natural and accurate descriptions in image cap-tioning has always been a challenge. In this paper, we pro-pose a novel recall mechanism to imitate the way human con-duct captioning. There are three parts in our recall mecha-nism…
We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence. By doing so, the model can learn more effectively compared to traditional attention-based approaches. To…
The core objective of image captioning is to achieve lossless semantic compression from visual signals into textual modalities. However, the reliance on manually curated reference texts for evaluation essentially forces models to mimic…
A wide range of image captioning models has been developed, achieving significant improvement based on popular metrics, such as BLEU, CIDEr, and SPICE. However, although the generated captions can accurately describe the image, they are…
Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model…
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image…
Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted…
Despite the fact that image captioning models have been able to generate impressive descriptions for a given image, challenges remain: (1) the controllability and diversity of existing models are still far from satisfactory; (2) models…
Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…
Image captioning is a challenging task that combines the field of computer vision and natural language processing. A variety of approaches have been proposed to achieve the goal of automatically describing an image, and recurrent neural…
Current image captioning methods are usually trained via (penalized) maximum likelihood estimation. However, the log-likelihood score of a caption does not correlate well with human assessments of quality. Standard syntactic evaluation…
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…
Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data. Many state-of-the-art self-training approaches hinge on different regularization methods to prevent…
Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with…