Huilin Xiong

Jiyuan Liu, Bingyi Lu, Mingkang Xiong et al.

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples, which are usually designed artificially to fool DNNs, but rarely exist in real-world scenarios. In this paper, we study the adversarial examples caused by raindrops, to demonstrate that there exist plenty of natural phenomena being able to work as adversarial attackers to DNNs. Moreover, we present a new approach to generate adversarial raindrops, denoted as AdvRD, using the generative adversarial network (GAN) technique to simulate natural raindrops. The images crafted by our AdvRD look very similar to the real-world raindrop images, statistically close to the distribution of true raindrop images, and more importantly, can perform strong adversarial attack to the state-of-the-art DNN models. On the other side, we show that the adversarial training using our AdvRD images can significantly improve the robustness of DNNs to the real-world raindrop attacks. Extensive experiments are carried out to demonstrate that the images crafted by AdvRD are visually and statistically close to the natural raindrop images, can work as strong attackers to DNN models, and also help improve the robustness of DNNs to raindrop attacks.

Guoqing Ma, Haoyang Huang, Kun Yan et al.

We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators.

Xinyu Xu, Huazhen Liu, Feiming Wei et al.

Point cloud is often regarded as a discrete sampling of Riemannian manifold and plays a pivotal role in the 3D image interpretation. Particularly, rotation perturbation, an unexpected small change in rotation caused by various factors (like equipment offset, system instability, measurement errors and so on), can easily lead to the inferior results in point cloud learning tasks. However, classical point cloud learning methods are sensitive to rotation perturbation, and the existing networks with rotation robustness also have much room for improvements in terms of performance and noise tolerance. Given these, this paper remodels the point cloud from the perspective of manifold as well as designs a manifold distillation method to achieve the robustness of rotation perturbation without any coordinate transformation. In brief, during the training phase, we introduce a teacher network to learn the rotation robustness information and transfer this information to the student network through online distillation. In the inference phase, the student network directly utilizes the original 3D coordinate information to achieve the robustness of rotation perturbation. Experiments carried out on four different datasets verify the effectiveness of our method. Averagely, on the Modelnet40 and ScanobjectNN classification datasets with random rotation perturbations, our classification accuracy has respectively improved by 4.92% and 4.41%, compared to popular rotation-robust networks; on the ShapeNet and S3DIS segmentation datasets, compared to the rotation-robust networks, the improvements of mIoU are 7.36% and 4.82%, respectively. Besides, from the experimental results, the proposed algorithm also shows excellent performance in resisting noise and outliers.

Xinyu Xu, Huazhen Liu, Tao Zhang et al.

Semantic segmentation is an important branch of image processing and computer vision. With the popularity of deep learning, various convolutional neural networks have been proposed for pixel-level classification and segmentation tasks. In practical scenarios, however, imaging angles are often arbitrary, encompassing instances such as water body images from remote sensing and capillary and polyp images in the medical domain, where prior orientation information is typically unavailable to guide these networks to extract more effective features. In this case, learning features from objects with diverse orientation information poses a significant challenge, as the majority of CNN-based semantic segmentation networks lack rotation equivariance to resist the disturbance from orientation information. To address this challenge, this paper first constructs a universal convolution-group framework aimed at more fully utilizing orientation information and equipping the network with rotation equivariance. Subsequently, we mathematically design a padding-based rotation equivariant convolution mode (PreCM), which is not only applicable to multi-scale images and convolutional kernels but can also serve as a replacement component for various types of convolutions, such as dilated convolutions, transposed convolutions, and asymmetric convolution. To quantitatively assess the impact of image rotation in semantic segmentation tasks, we also propose a new evaluation metric, Rotation Difference (RD). The replacement experiments related to six existing semantic segmentation networks on three datasets show that, the average Intersection Over Union (IOU) of their PreCM-based versions respectively improve 6.91%, 10.63%, 4.53%, 5.93%, 7.48%, 8.33% compared to their original versions in terms of random angle rotation. And the average RD values are decreased by 3.58%, 4.56%, 3.47%, 3.66%, 3.47%, 3.43% respectively.