Related papers: Beyond Seen Bounds: Class-Centric Polarization for…

In this paper we propose a sequential learning framework for Domain Generalization (DG), the problem of training a model that is robust to domain shift by design. Various DG approaches have been proposed with different motivating…

Deep learning often struggles when training and test data distributions differ. Traditional domain generalization (DG) tackles this by including data from multiple source domains, which is impractical due to expensive data collection and…

Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of…

Distributional shift between domains poses great challenges to modern machine learning algorithms. The domain generalization (DG) signifies a popular line targeting this issue, where these methods intend to uncover universal patterns across…

Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios. Existing DG methods assume that the do-main label is known.However, in real-world applications,…

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs…

Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities which not only generalize from training data to identically distributed test…

Conventional Domain Generalization (CDG) utilizes multiple labeled source datasets to train a generalizable model for unseen target domains. However, due to expensive annotation costs, the requirements of labeling all the source data are…

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance. To achieve this, we train a…

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image…

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…

Recent point cloud understanding research suffers from performance drops on unseen data, due to the distribution shifts across different domains. While recent studies use Domain Generalization (DG) techniques to mitigate this by learning…

Supervised learning results typically rely on assumptions of i.i.d. data. Unfortunately, those assumptions are commonly violated in practice. In this work, we tackle such problem by focusing on domain generalization: a formalization where…

In Domain Generalization (DG) tasks, models are trained by using only training data from the source domains to achieve generalization on an unseen target domain, this will suffer from the distribution shift problem. So it's important to…

Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a…

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications.…

Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives.…

Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple…