MAAD-Face: A Massively Annotated Attribute Dataset for Face Images

用于评估人脸识别中合成数据与真实数据的大规模标注数据集

Massively Annotated Datasets for Assessment of Synthetic and Real Data in Face Recognition

该研究利用大规模属性分类器（MAC）为四个真实和合成人脸数据集创建标注，通过Kullback-Leibler散度分析属性分布差异，发现真实样本能解释合成分布，但反之不成立。

Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset

Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model se…

基于大规模标注数据库的Deepfake检测公平性分析

Analyzing Fairness in Deepfake Detection With Massively Annotated Databases

本研究为5个主流Deepfake数据集添加47种属性的大规模标注，分析3种最优检测骨干模型的偏差成因，发现数据集多样性不足且模型受属性影响存在公平性问题，相关资源已公开以助力偏差缓解研究。

Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices

Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications. In this paper, we propose a novel method based on Deep Learning and Guided Filter, called Inductive Guided Filter, which can tackle the real-time general image matting task on mobile devices. We design a lightweight hourglass network to parameterize the original Guided Filter method th…

Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection

Accurate Computer-Assisted Diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis. Unfortunately, in medical imaging, most available datasets are small/fragmented. To tackle this, as a Data Augmentation (DA) method, 3D conditional Generative Adversarial Networks (GANs) can synthesize desired realistic/diverse 3D images as additional training data. However, no 3D conditional GAN-based DA approach exists for general bounding box-based 3D object detection, while it can locate disease areas with physicians' minimum annotation cost, unli…

基于证据决策的合成人脸检测与不确定性驱动主动学习

Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning

本文提出EMSFD方法，通过Dirichlet分布建模类证据并引入模型不确定性提升检测可靠性与泛化能力，实验显示其在准确性上比现有方法提高15%。