With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that p...
详细信息
Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative task...
详细信息
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely...
Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While th...
Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of catastrophic forgetting in pre-trained backbone has been extensively studied for fine-tuning, its potential bias from the corresponding pre-training task and data, attracts less attention. In this work, we investigate this problem by demonstrating that the obtained classifier after fine-tuning will be close to that induced by the pre-trained model. To reduce the bias in the classifier effectively, we introduce a reference distribution obtained from a fixed text classifier, which can help regularize the learned vision classifier. The proposed method, Text Supervised fine-tuning (TeS), is evaluated with diverse pre-trained vision models including ResNet and ViT, and text encoders including BERT and CLIP, on 11 downstream tasks. The consistent improvement with a clear margin over distinct scenarios confirms the effectiveness of our proposal. Code is available at https://***/idstcv/TeS.
The detection of induced pluripotent stem cell (iPSC) colonies often needs the precise extraction of the colony features. However, existing computerized systems relied on segmentation of contours by preprocessing for ...
详细信息
Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often f...
Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients’ data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. ...
详细信息
Based on the message-passing paradigm, there has been an amount of research proposing diverse and impressive feature propagation mechanisms to improve the performance of GNNs. However, less focus has been put on featu...
详细信息
Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal int...
详细信息
We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR...
详细信息
We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.
暂无评论