Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models

The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These methods can produce high-fidelity images and lifelike avatars, highlighting the need for robust detection methods. In response, an unsupervised training technique is proposed that enables the model to extract comprehensive features from the Fourier spectrum magnitude, thereby overcoming the challenges of reconstructing the spectrum due to its centrosymmetric properties. By leveraging the spectral domain and dynamically combining it with spatial domain information, we create a robust multimodal detector that demonstrates superior generalization capabilities in identifying challenging synthetic images generated by the latest image synthesis techniques. To address the absence of a 3D neural rendering-based fake image database, we develop a comprehensive database that includes images generated by diverse neural rendering techniques, providing a robust foundation for evaluating and advancing detection methods.

Neural Scoring, Not Embedding: A Novel Framework for Robust Speaker Verification

Current mainstream speaker verification systems are predominantly based on the concept of ``speaker embedding", which transforms variable-length speech signals into fixed-length speaker vectors, followed by verification based on cosine similarity between the embeddings of the enrollment and test utterances. However, this approach suffers from considerable performance degradation in the presence of severe noise and interference speakers. This paper introduces Neural Scoring, a novel framework that re-treats speaker verification as a scoring task using a Transformer-based architecture. The proposed method first extracts an embedding from the enrollment speech and frame-level features from the test speech. A Transformer network then generates a decision score that quantifies the likelihood of the enrolled speaker being present in the test speech. We evaluated Neural Scoring on the VoxCeleb dataset across five test scenarios, comparing it with the state-of-the-art embedding-based approach. While Neural Scoring achieves comparable performance to the state-of-the-art under the benchmark (clean) test condition, it demonstrates a remarkable advantage in the four complex scenarios, achieving an overall 64.53% reduction in equal error rate (EER) compared to the baseline.

Simple and Fast Distillation of Diffusion Models

Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based accelerated sampling methods have been developed recently. However, they generally require time-consuming fine tuning with elaborate designs to achieve satisfactory performance in a specific number of function evaluation (NFE), making them difficult to employ in practice. To address this issue, we propose Simple and Fast Distillation (SFD) of diffusion models, which simplifies the paradigm used in existing methods and largely shortens their fine-tuning time up to 1000$\times$. We begin with a vanilla distillation-based sampling method and boost its performance to state of the art by identifying and addressing several small yet vital factors affecting the synthesis efficiency and quality. Our method can also achieve sampling with variable NFEs using a single distilled model. Extensive experiments demonstrate that SFD strikes a good balance between the sample quality and fine-tuning costs in few-step image generation task. For example, SFD achieves 4.53 FID (NFE=2) on CIFAR-10 with only 0.64 hours of fine-tuning on a single NVIDIA A100 GPU. Our code is available at https://github.com/zju-pi/diff-sampler.

A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition

Data augmentation (DA) has played a pivotal role in the success of deep speaker recognition. Current DA techniques primarily focus on speaker-preserving augmentation, which does not change the speaker trait of the speech and does not create new speakers. Recent research has shed light on the potential of speaker augmentation, which generates new speakers to enrich the training dataset. In this study, we delve into two speaker augmentation approaches: speed perturbation (SP) and vocal tract length perturbation (VTLP). Despite the empirical utilization of both methods, a comprehensive investigation into their efficacy is lacking. Our study, conducted using two public datasets, VoxCeleb and CN-Celeb, revealed that both SP and VTLP are proficient at generating new speakers, leading to significant performance improvements in speaker recognition. Furthermore, they exhibit distinct properties in sensitivity to perturbation factors and data complexity, hinting at the potential benefits of their fusion. Our research underscores the substantial potential of speaker augmentation, highlighting the importance of in-depth exploration and analysis.

On the Trajectory Regularity of ODE-based Diffusion Sampling

Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models. We characterize an implicit denoising trajectory and discuss its vital role in forming the coupled sampling trajectory with a strong shape regularity, regardless of the generated content. We also describe a dynamic programming-based scheme to make the time schedule in sampling better fit the underlying trajectory structure. This simple strategy requires minimal modification to any given ODE-based numerical solvers and incurs negligible computational cost, while delivering superior performance in image generation, especially in $5\sim 10$ function evaluations.

Adversarial Data Augmentation for Robust Speaker Verification

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural networks to learn speaker-related representations while disregarding irrelevant acoustic variations, thereby improving robustness and generalization. However, a potential issue with the vanilla DA is augmentation residual, i.e., unwanted distortion caused by different types of augmentation. To address this problem, this paper proposes a novel approach called adversarial data augmentation (A-DA) which combines DA with adversarial learning. Specifically, it involves an additional augmentation classifier to categorize various augmentation types used in data augmentation. This adversarial learning empowers the network to generate speaker embeddings that can deceive the augmentation classifier, making the learned speaker embeddings more robust in the face of augmentation variations. Experiments conducted on VoxCeleb and CN-Celeb datasets demonstrate that our proposed A-DA outperforms standard DA in both augmentation matched and mismatched test conditions, showcasing its superior robustness and generalization against acoustic variations.

Fast ODE-based Sampling for Diffusion Models in Around 5 Steps

Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently, various fast samplers utilizing higher-order ODE solvers have emerged and achieved better performance than the initial first-order one. However, these numerical methods inherently result in certain approximation errors, which significantly degrades sample quality with extremely small NFE (e.g., around 5). In contrast, based on the geometric observation that each sampling trajectory almost lies in a two-dimensional subspace embedded in the ambient space, we propose Approximate MEan-Direction Solver (AMED-Solver) that eliminates truncation errors by directly learning the mean direction for fast diffusion sampling. Besides, our method can be easily used as a plugin to further improve existing ODE-based samplers. Extensive experiments on image synthesis with the resolution ranging from 32 to 256 demonstrate the effectiveness of our method. With only 5 NFE, we achieve 7.14 FID on CIFAR-10, 13.75 FID on ImageNet 64$\times$64, and 12.79 FID on LSUN Bedroom. Our code is available at https://github.com/zhyzhouu/amed-solver.

An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition

Multi-genre speaker recognition is becoming increasingly popular due to its ability to better represent the complexities of real-world applications. However, a major challenge is the significant shift in the distribution of speaker vectors across different genres. While distribution alignment is a common approach to address this challenge, previous studies have mainly focused on aligning a source domain with a target domain, and the performance of multi-genre data is unknown. This paper presents a comprehensive study of mainstream distribution alignment methods on multi-genre data, where multiple distributions need to be aligned. We analyze various methods both qualitatively and quantitatively. Our experiments on the CN-Celeb dataset show that within-between distribution alignment (WBDA) performs relatively better. However, we also found that none of the investigated methods consistently improved performance in all test cases. This suggests that solely aligning the distributions of speaker vectors may not fully address the challenges posed by multi-genre speaker recognition. Further investigation is necessary to develop a more comprehensive solution.

A Geometric Perspective on Diffusion Models

Recent years have witnessed significant progress in developing efficient training and fast sampling approaches for diffusion models. A recent remarkable advancement is the use of stochastic differential equations (SDEs) to describe data perturbation and generative modeling in a unified mathematical framework. In this paper, we reveal several intriguing geometric structures of diffusion models and contribute a simple yet powerful interpretation to their sampling dynamics. Through carefully inspecting a popular variance-exploding SDE and its marginal-preserving ordinary differential equation (ODE) for sampling, we discover that the data distribution and the noise distribution are smoothly connected with an explicit, quasi-linear sampling trajectory, and another implicit denoising trajectory, which even converges faster in terms of visual quality. We also establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the score deviation. These new geometric observations enable us to improve previous sampling algorithms, re-examine latent interpolation, as well as re-explain the working principles of distillation-based fast sampling techniques.

HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains

High dynamic range (HDR) video reconstruction is attracting more and more attention due to the superior visual quality compared with those of low dynamic range (LDR) videos. The availability of LDR-HDR training pairs is essential for the HDR reconstruction quality. However, there are still no real LDR-HDR pairs for dynamic scenes due to the difficulty in capturing LDR-HDR frames simultaneously. In this work, we propose to utilize a staggered sensor to capture two alternate exposure images simultaneously, which are then fused into an HDR frame in both raw and sRGB domains. In this way, we build a large scale LDR-HDR video dataset with 85 scenes and each scene contains 60 frames. Based on this dataset, we further propose a Raw-HDRNet, which utilizes the raw LDR frames as inputs. We propose a pyramid flow-guided deformation convolution to align neighboring frames. Experimental results demonstrate that 1) the proposed dataset can improve the HDR reconstruction performance on real scenes for three benchmark networks; 2) Compared with sRGB inputs, utilizing raw inputs can further improve the reconstruction quality and our proposed Raw-HDRNet is a strong baseline for raw HDR reconstruction. Our dataset and code will be released after the acceptance of this paper.