No abstract

We propose to detect Deepfake generated by face manipulation based on one of their fundamental features: images are blended by patches from multiple sources, carrying distinct and persistent source features. In particular, we propose a novel representation learning approach for this task, called patch-wise consistency learning (PCL). It learns by measuring the consistency of image source features, resulting to representation with good interpretability and robustness to multiple forgery methods. We develop an inconsistency image generator (I2G) to generate training data for PCL and boost its robustness. We evaluate our approach on seven popular Deepfake detection datasets. Our model achieves superior detection accuracy and generalizes well to unseen generation methods. On average, our model outperforms the state-of-the-art in terms of AUC by 2% and 8% in the in-and cross-dataset evaluation, respectively.

No abstract

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational datasets, are inadequate for this task because they conflate algorithmic bias with dataset bias.To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change. Our proposed method is based on generating synthetic "transects" of matched sample images that are designed to differ along specific attributes while leaving other attributes constant. A crucial aspect of our approach is relying on the perception of human observers, both to guide manipulations, and to measure algorithmic bias.Besides allowing the measurement of algorithmic bias, synthetic transects have other advantages with respect to observational datasets: they sample attributes more evenly, allowing for more straightforward bias analysis on minority and intersectional groups, they enable prediction of bias in new scenarios, they greatly reduce ethical and legal challenges, and they are economical and fast to obtain, helping make bias testing affordable and widely available.We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms. The two methods reach different conclusions. While the observational method reports gender and skin color biases, the experimental method reveals biases due to gender, hair length, age, and facial hair.

Despite much research progress in image semantic segmentation, it remains challenging under adverse environmental conditions caused by imaging limitations of visible spectrum. While thermal infrared cameras have several advantages over cameras for the visible spectrum, such as operating in total darkness, insensitive to illumination variations, robust to shadow effects and strong ability to penetrate haze and smog. These advantages of thermal infrared cameras make the segmentation of semantic objects in day and night. In this paper we propose a novel network architecture, called edge-conditioned convolutional neural network (EC-CNN), for thermal image semantic segmentation. Particularly, we elaborately design a gated feature-wise transform layer in EC-CNN to adaptively incorporate edge prior knowledge. The whole EC-CNN is endto-end trained, and can generate high-quality segmentation results with the edge guidance. Meanwhile, we also introduce a new benchmark dataset named "Segment Objects in Day And night"(SODA) for comprehensive evaluations in thermal image semantic segmentation. SODA contains over 7,168 manually annotated and synthetically generated thermal images with 20 semantic region labels and from a broad range of viewpoints and scene complexities. Extensive experiments on SODA demonstrate the effectiveness of the proposed EC-CNN against the state-ofthe-art methods.

No abstract

Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the robustness of the system and reduce human labeling costs. In this study, we introduce an unsupervised Adversarial Discriminative Domain Adaptation (ADDA) method to effectively learn an asymmetric mapping that adapts the target domain encoder to the source domain, where the target domain and source domain are speech data from different languages. ADDA, together with a popular Domain Adversarial Training (DAT) approach, are evaluated on a cross-lingual speaker verification task: the training data is in English from NIST SRE04-08, Mixer 6 and Switchboard, and the test data is in Chinese from AISHELL-I. We show that with the ADDA adaptation, Equal Error Rate (EER) of the x-vector system decreases from 9.331% to 7.645%, relatively 18.07% reduction of EER, and 6.32% reduction from DAT as well. Further data analysis of ADDA adapted speaker embedding shows that the learned speaker embeddings can perform well on speaker classification for the target domain data, and are less dependent with respect to the shift in language.

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo speaker embedding system utilizes a queue to maintain a large set of negative examples. We show that better speaker embeddings can be learned by momentum contrastive learning. Next, alternative augmentation strategies are explored to normalize extrinsic speaker variabilities of two random segments from the same speech utterance. Specifically, augmentation in the waveform largely improves the speaker representations for SV tasks. The proposed MoCo speaker embedding is further improved when a prototypical memory bank is introduced, which encourages the speaker embeddings to be closer to their assigned prototypes with an intermediate clustering step. In addition, we generalize the self-supervised framework to a semi-supervised scenario where only a small portion of the data is labeled. Comprehensive experiments on the Voxceleb dataset demonstrate that our proposed selfsupervised approach achieves competitive performance compared with existing techniques, and can approach fully supervised results with partially labeled data.