Related papers: Training-Only Heterogeneous Image-Patch-Text Graph…

Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that…

State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated…

Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios. Despite the potential for deeper…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current…

Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be…

Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the…

Recently supervised learning rapidly develops in scene text segmentation. However, the lack of high-quality datasets and the high cost of pixel annotation greatly limit the development of them. Considering the well-performed few-shot…

Graph-based multi-view clustering has become an active topic due to the efficiency in characterizing both the complex structure and relationship between multimedia data. However, existing methods have the following shortcomings: (1) They…

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text…

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…

Few-shot learning (FSL), purposing to resolve the problem of data-scarce, has attracted considerable attention in recent years. A popular FSL framework contains two phases: (i) the pre-train phase employs the base data to train a CNN-based…

Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often…

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…

Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The majority of existing methods are performed in an unsupervised…

Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classification. However,…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional…

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods…

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on…

Multi-label classification is an essential task utilized in a wide variety of real-world applications. Multi-label zero-shot learning is a method for classifying images into multiple unseen categories for which no training data is…