Related papers: Domain-Inspired Sharpness-Aware Minimization Under…

Machine learning algorithms minimizing the average training loss usually suffer from poor generalization performance due to the greedy exploitation of correlations among the training data, which are not stable under distributional shifts.…

Domain adaptation (DA) is a technique that transfers predictive models trained on a labeled source domain to an unlabeled target domain, with the core difficulty of resolving distributional shift between domains. Currently, most popular DA…

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, etc. They attempt to reduce domain bias-induced performance degradation while also promoting model application…

Recent advancements in learning algorithms have demonstrated that the sharpness of the loss surface is an effective measure for improving the generalization gap. Building upon this concept, Sharpness-Aware Minimization (SAM) was proposed to…

Dataset Condensation (DC) has emerged as a promising solution to mitigate the computational and storage burdens associated with training deep learning models. However, existing DC methods largely overlook the multi-domain nature of modern…

Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data, especially when encountering the common challenge in time series data that distribution shifts occur between training and testing datasets. In…

Multi-task learning (MTL) enables a joint model to capture commonalities across multiple tasks, reducing computation costs and improving data efficiency. However, a major challenge in MTL optimization is task conflicts, where the task…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades…

Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing…

Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as…

In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of…

Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are usually prone to errors due to domain shift. After…

The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain that the model can train on. Classification becomes more challenging when dealing with new data from a different…

Deep learning models usually suffer from domain shift issues, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate the single-source domain generalization problem: training a…

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Most state-of-the-art deep domain adaptation techniques align source and target samples in a global fashion. That is, after alignment, each source sample is expected to become similar to any target sample. However, global alignment may not…

Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in how to determine whether the target samples belong to common…

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in…