Related papers: DogFit: Domain-guided Fine-tuning for Efficient Tr…

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Cross-modal image translation remains brittle and inefficient. Standard diffusion approaches often rely on a single, global linear transfer between domains. We find that this shortcut forces the sampler to traverse off-manifold, high-cost…

Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autoregressive modeling. Yet this performance typically depends on large training datasets,…

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

Resource-constrained IoT devices increasingly rely on deep learning models, however, these models experience significant accuracy drops due to domain shifts when encountering variations in lighting, weather, and seasonal conditions. While…

Recommender systems are often asked to serve multiple recommendation scenarios or domains. Fine-tuning a pre-trained CTR model from source domains and adapting it to a target domain allows knowledge transferring. However, optimizing all the…

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by…

Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Deep-learning methods offer unsurpassed recognition performance in a wide range of domains, including fine-grained recognition tasks. However, in most problem areas there are insufficient annotated training samples. Therefore, the topic of…

Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available. This paper proposes…

Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited…

Addressing shifts in data distributions is an important prerequisite for the deployment of deep learning models to real-world settings. A general approach to this problem involves the adjustment of models to a new domain through transfer…

Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relationships in tabular data. Existing approaches rely either on…

Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained models to new tasks.…

Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a…

In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific…

Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain policy transfer methods mostly aim at learning domain…

Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for model adaptation methods, since adapting to domain shifts…