相关论文: Beyond Overfitting: Doubly Adaptive Dropout for Ge…

Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons. Since covering all domains with annotated…

Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across different domains due to insufficient intrinsic interactions. These…

Different camera sensors have different noise patterns, and thus an image denoising model trained on one sensor often does not generalize well to a different sensor. One plausible solution is to collect a large dataset for each sensor for…

Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN). However, to allow networks to generalize knowledge from…

Micro-expression (ME) action units (Micro-AUs) provide objective clues for fine-grained genuine emotion analysis. Most existing Micro-AU detection methods learn AU features from the whole facial image/video, which conflicts with the…

Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can…

It is challenging to recognize facial action unit (AU) from spontaneous facial displays, especially when they are accompanied by speech. The major reason is that the information is extracted from a single source, i.e., the visual channel,…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding…

Fall detection (FD) systems are important assistive technologies for healthcare that can detect emergency fall events and alert caregivers. However, it is not easy to obtain large-scale annotated fall events with various specifications of…

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task…

Recent advancements in dense out-of-distribution (OOD) detection have primarily focused on scenarios where the training and testing datasets share a similar domain, with the assumption that no domain shift exists between them. However, in…

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model training, due to…

Reducing feature redundancy has shown beneficial effects for improving the accuracy of deep learning models, thus it is also indispensable for the models of unsupervised domain adaptation (UDA). Nevertheless, most recent efforts in the…

Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets.…

Nowadays, visual data forgery detection plays an increasingly important role in social and economic security with the rapid development of generative models. Existing face forgery detectors still can't achieve satisfactory performance…

Overfitting remains a significant challenge in deep learning, often arising from data outliers, noise, and limited training data. To address this, the Divide2Conquer (D2C) method was previously proposed, which partitions training data into…

Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…

Unsupervised domain adaptive object detection is a challenging vision task where object detectors are adapted from a label-rich source domain to an unlabeled target domain. Recent advances prove the efficacy of the adversarial based domain…

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations. Existing UCIR methods, which align cross-domain features for the entire image, often…