Related papers: Set Pivot Learning: Redefining Generalized Segment…
Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting…
Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on access to the target domain during training, meaning the…
Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen…
In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…
Domain generalization (DG) aims to avoid the performance degradation of the model when the distribution shift between the limited training data and unseen test data occurs. Recently, foundation models with enormous parameters have been…
Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…
Domain Generalization (DG) aims to generalize to arbitrary unseen domains. A promising approach to improve model generalization in DG is the identification of flat minima. One typical method for this task is SWAD, which involves averaging…
Domain generalization (DG) aims to learn a model from source domains and apply it to unseen target domains with out-of-distribution data. Owing to CLIP's strong ability to encode semantic concepts, it has attracted increasing interest in…
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…
Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often favoring the classes…
Semantic segmentation networks trained under full supervision for one type of lidar fail to generalize to unseen lidars without intervention. To reduce the performance gap under domain shifts, a recent trend is to leverage vision foundation…
Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared across domains hinders…
Model generalization capacity at domain shift (e.g., various imaging protocols and scanners) is crucial for deep learning methods in real-world clinical deployment. This paper tackles the challenging problem of domain generalization, i.e.,…
Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario…
Traditional deep learning-based visual imitation learning techniques require a large amount of demonstration data for model training, and the pre-trained models are difficult to adapt to new scenarios. To address these limitations, we…
Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…
Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…
Domain generalization seeks to develop models trained on a limited set of source domains that are capable of generalizing effectively to unseen target domains. While the predominant approach leverages large-scale pre-trained vision models…
Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is…
Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such…