通常承认，巨额（培训）数据的可用性是人工智能（AI）最近进步的最重要因素之一。但是，数据集通常用于狭窄的AI子区域中的特定任务，并且没有统一的方式来管理和访问它们。这不仅在培训或部署机器学习模型时创造了不必要的开销，但也限制了对数据的理解，这对于以数据为中心的AI非常重要。在本文中，我们向不同数据集的统一框架展示了我们的愿景，以便可以轻松地集成和查询，例如，使用标准查询语言。我们在持续的工作中展示了这一点，为计算机愿景中的数据集创建了一个框架，并在不同的场景中显示了它的优势。我们的演示可在https://vision.semkg.org中获得。

There is no settled universal 3D representation for geometry with many alternatives such as point clouds, meshes, implicit functions, and voxels to name a few. In this work, we present a new, compelling alternative for representing shapes using a sequence of cross-sectional closed loops. The loops across all planes form an organizational hierarchy which we leverage for autoregressive shape synthesis and editing. Loops are a non-local description of the underlying shape, as simple loop manipulations (such as shifts) result in significant structural changes to the geometry. This is in contrast to manipulating local primitives such as points in a point cloud or a triangle in a triangle mesh. We further demonstrate that loops are intuitive and natural primitive for analyzing and editing shapes, both computationally and for users.

Adversarial machine learning has been both a major concern and a hot topic recently, especially with the ubiquitous use of deep neural networks in the current landscape. Adversarial attacks and defenses are usually likened to a cat-and-mouse game in which defenders and attackers evolve over the time. On one hand, the goal is to develop strong and robust deep networks that are resistant to malicious actors. On the other hand, in order to achieve that, we need to devise even stronger adversarial attacks to challenge these defense models. Most of existing attacks employs a single $\ell_p$ distance (commonly, $p\in\{1,2,\infty\}$) to define the concept of closeness and performs steepest gradient ascent w.r.t. this $p$-norm to update all pixels in an adversarial example in the same way. These $\ell_p$ attacks each has its own pros and cons; and there is no single attack that can successfully break through defense models that are robust against multiple $\ell_p$ norms simultaneously. Motivated by these observations, we come up with a natural approach: combining various $\ell_p$ gradient projections on a pixel level to achieve a joint adversarial perturbation. Specifically, we learn how to perturb each pixel to maximize the attack performance, while maintaining the overall visual imperceptibility of adversarial examples. Finally, through various experiments with standardized benchmarks, we show that our method outperforms most current strong attacks across state-of-the-art defense mechanisms, while retaining its ability to remain clean visually.

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely \ourmodel, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.

The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs, making them unfit for in-the-wild low-quality (LQ) images, which are common inputs for manipulation. In this work, we bridge this gap by proposing a novel GAN structure that allows for generating images with controllable quality. The network can synthesize various image degradation and restore the sharp image via a quality control code. Our proposed QC-StyleGAN can directly edit LQ images without altering their quality by applying GAN inversion and manipulation techniques. It also provides for free an image restoration solution that can handle various degradations, including noise, blur, compression artifacts, and their mixtures. Finally, we demonstrate numerous other applications such as image degradation synthesis, transfer, and interpolation.

Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used in real-time applications. A recent DiffusionGAN method significantly decreases the models' running time by reducing the number of sampling steps from thousands to several, but their speeds still largely lag behind the GAN counterparts. This paper aims to reduce the speed gap by proposing a novel wavelet-based diffusion structure. We extract low-and-high frequency components from both image and feature levels via wavelet decomposition and adaptively handle these components for faster processing while maintaining good generation quality. Furthermore, we propose to use a reconstruction term, which effectively boosts the model training convergence. Experimental results on CelebA-HQ, CIFAR-10, LSUN-Church, and STL-10 datasets prove our solution is a stepping-stone to offering real-time and high-fidelity diffusion models. Our code and pre-trained checkpoints will be available at \url{https://github.com/VinAIResearch/WaveDiff.git}.

A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations for tasks ranging from object recognition and semantic segmentation to optical flow estimation and novel view synthesis of 3D scenes. In this work, we aim to learn dense discriminative object representations for low-shot category recognition without requiring any category labels. To this end, we propose Deep Object Patch Encodings (DOPE), which can be trained from multiple views of object instances without any category or semantic object part labels. To train DOPE, we assume access to sparse depths, foreground masks and known cameras, to obtain pixel-level correspondences between views of an object, and use this to formulate a self-supervised learning task to learn discriminative object patches. We find that DOPE can directly be used for low-shot classification of novel categories using local-part matching, and is competitive with and outperforms supervised and self-supervised learning baselines. Code and data available at https://github.com/rehg-lab/dope_selfsup.

The dynamics of a turbulent flow tend to occupy only a portion of the phase space at a statistically stationary regime. From a dynamical systems point of view, this portion is the attractor. The knowledge of the turbulent attractor is useful for two purposes, at least: (i) We can gain physical insight into turbulence (what is the shape and geometry of the attractor?), and (ii) it provides the minimal number of degrees of freedom to accurately describe the turbulent dynamics. Autoencoders enable the computation of an optimal latent space, which is a low-order representation of the dynamics. If properly trained and correctly designed, autoencoders can learn an approximation of the turbulent attractor, as shown by Doan, Racca and Magri (2022). In this paper, we theoretically interpret the transformations of an autoencoder. First, we remark that the latent space is a curved manifold with curvilinear coordinates, which can be analyzed with simple tools from Riemann geometry. Second, we characterize the geometrical properties of the latent space. We mathematically derive the metric tensor, which provides a mathematical description of the manifold. Third, we propose a method -- proper latent decomposition (PLD) -- that generalizes proper orthogonal decomposition of turbulent flows on the autoencoder latent space. This decomposition finds the dominant directions in the curved latent space. This theoretical work opens up computational opportunities for interpreting autoencoders and creating reduced-order models of turbulent flows.

Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated data, the scene graph generated from current methodologies can be biased toward common, non-informative relationship labels. Relationship can sometimes be non-mutually exclusive, which can be described from multiple perspectives like geometrical relationships or semantic relationships, making it even more challenging to predict the most suitable relationship label. In this work, we proposed the SG-Shuffle pipeline for scene graph generation with 3 components: 1) Parallel Transformer Encoder, which learns to predict object relationships in a more exclusive manner by grouping relationship labels into groups of similar purpose; 2) Shuffle Transformer, which learns to select the final relationship labels from the category-specific feature generated in the previous step; and 3) Weighted CE loss, used to alleviate the training bias caused by the imbalanced dataset.

Solving the analytical inverse kinematics (IK) of redundant manipulators in real time is a difficult problem in robotics since its solution for a given target pose is not unique. Moreover, choosing the optimal IK solution with respect to application-specific demands helps to improve the robustness and to increase the success rate when driving the manipulator from its current configuration towards a desired pose. This is necessary, especially in high-dynamic tasks like catching objects in mid-flights. To compute a suitable target configuration in the joint space for a given target pose in the trajectory planning context, various factors such as travel time or manipulability must be considered. However, these factors increase the complexity of the overall problem which impedes real-time implementation. In this paper, a real-time framework to compute the analytical inverse kinematics of a redundant robot is presented. To this end, the analytical IK of the redundant manipulator is parameterized by so-called redundancy parameters, which are combined with a target pose to yield a unique IK solution. Most existing works in the literature either try to approximate the direct mapping from the desired pose of the manipulator to the solution of the IK or cluster the entire workspace to find IK solutions. In contrast, the proposed framework directly learns these redundancy parameters by using a neural network (NN) that provides the optimal IK solution with respect to the manipulability and the closeness to the current robot configuration. Monte Carlo simulations show the effectiveness of the proposed approach which is accurate and real-time capable ($\approx$ \SI{32}{\micro\second}) on the KUKA LBR iiwa 14 R820.