Related papers: Self-Supervised Open-Ended Classification with Sma…

Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images…

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions…

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on…

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for training, which…

While large language-image pre-trained models like CLIP offer powerful generic features for image clustering, existing methods typically freeze the encoder. This creates a fundamental mismatch between the model's task-agnostic…

In this paper, we address the problem of searching for semantically similar images from a large database. We present a compact coding approach, supervised quantization. Our approach simultaneously learns feature selection that linearly…

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…

Recent advancements in large-scale pretraining in natural language processing have enabled pretrained vision-language models such as CLIP to effectively align images and text, significantly improving performance in zero-shot image…

Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label information; recent…

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

Text-to-image retrieval is a critical task for managing diverse visual content, but common benchmarks for the task rely on small, single-domain datasets that fail to capture real-world complexity. Pre-trained vision-language models tend to…

Vision-language models (VLMs) pre-trained on large, heterogeneous data sources are becoming increasingly popular, providing rich multi-modal embeddings that enable efficient transfer to new tasks. A particularly relevant application is…

Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features…

Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images…

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this…

Image clustering is a classic problem in computer vision, which categorizes images into different groups. Recent studies utilize nouns as external semantic knowledge to improve clustering performance. However, these methods often overlook…

The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic…

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…