Related papers: Compositional Feature Augmentation for Unbiased Sc…

Learning similarity between scene graphs and images aims to estimate a similarity score given a scene graph and an image. There is currently no research dedicated to this task, although it is critical for scene graph generation and…

Scene-Graph Generation (SGG) seeks to recognize objects in an image and distill their salient pairwise relationships. Most methods depend on dataset-specific supervision to learn the variety of interactions, restricting their usefulness in…

Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available. Existing DGSS methods primarily standardize the feature…

Today's scene graph generation (SGG) models typically require abundant manual annotations to learn new predicate types. Therefore, it is difficult to apply them to real-world applications with massive uncommon predicate categories whose…

Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space. However, we argue that a global CFG scale results in…

Single-source domain generalization (SDG) for object detection is a challenging yet essential task as the distribution bias of the unseen domain degrades the algorithm performance significantly. However, existing methods attempt to extract…

Graph Convolutional Networks (GCNs) have become increasingly popular in recommendation systems. However, recent studies have shown that GCN-based models will cause sensitive information to disseminate widely in the graph structure,…

Recently, the attention-enriched encoder-decoder framework has aroused great interest in image captioning due to its overwhelming progress. Many visual attention models directly leverage meaningful regions to generate image descriptions.…

By retrieving contexts from knowledge graphs, graph-based retrieval-augmented generation (GraphRAG) enhances large language models (LLMs) to generate quality answers for user questions. Many GraphRAG methods have been proposed and reported…

Graphs serve as versatile data structures in numerous real-world domains-including social networks, molecular biology, and knowledge graphs-by capturing intricate relational information among entities. Among graph-based learning techniques,…

Addressing the challenge of removing atmospheric fog or haze from digital images, known as image dehazing, has recently gained significant traction in the computer vision community. Although contemporary dehazing models have demonstrated…

Structural knowledge graph foundation models aim to generalize reasoning to completely new graphs with unseen entities and relations. A key limitation of existing approaches like Ultra is their reliance on a single relational transformation…

Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors. Due to the lack of proper interaction with image texture during structure reconstruction, however, current solutions…

Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects…

Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting accuracy inconsistencies across varied data subpopulations.…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs…

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…