Existing state-of-the-art 3D point cloud instance segmentation methods rely on a grouping-based approach that groups points to obtain object instances. Despite improvement in producing accurate segmentation results, these methods lack scalability and commonly require dividing large input into multiple parts. To process a scene with millions of points, the existing fastest method SoftGroup \cite{vu2022softgroup} requires tens of seconds, which is under satisfaction. Our finding is that $k$-Nearest Neighbor ($k$-NN), which serves as the prerequisite of grouping, is a computational bottleneck. This bottleneck severely worsens the inference time in the scene with a large number of points. This paper proposes SoftGroup++ to address this computational bottleneck and further optimize the inference speed of the whole network. SoftGroup++ is built upon SoftGroup, which differs in three important aspects: (1) performs octree $k$-NN instead of vanilla $k$-NN to reduce time complexity from $\mathcal{O}(n^2)$ to $\mathcal{O}(n \log n)$, (2) performs pyramid scaling that adaptively downsamples backbone outputs to reduce search space for $k$-NN and grouping, and (3) performs late devoxelization that delays the conversion from voxels to points towards the end of the model such that intermediate components operate at a low computational cost. Extensive experiments on various indoor and outdoor datasets demonstrate the efficacy of the proposed SoftGroup++. Notably, SoftGroup++ processes large scenes of millions of points by a single forward without dividing the input into multiple parts, thus enriching contextual information. Especially, SoftGroup++ achieves 2.4 points AP$_{50}$ improvement while nearly $6\times$ faster than the existing fastest method on S3DIS dataset. The code and trained models will be made publicly available.
Convolutional neural networks (CNN) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete grid into a reduced grid with the same connectivity and allows reduction functions to take into account all the pixels of an image. However, a pooling satisfying such properties does not exist for graphs. Indeed, some methods are based on a vertex selection step which induces an important loss of information. Other methods learn a fuzzy clustering of vertex sets which induces almost complete reduced graphs. We propose to overcome both problems using a new pooling method, named MIVSPool. This method is based on a selection of vertices called surviving vertices using a Maximal Independent Vertex Set (MIVS) and an assignment of the remaining vertices to the survivors. Consequently, our method does not discard any vertex information nor artificially increase the density of the graph. Experimental results show an increase in accuracy for graph classification on various standard datasets.
Perception is one of the crucial module of the autonomous driving system, which has made great progress recently. However, limited ability of individual vehicles results in the bottleneck of improvement of the perception performance. To break through the limits of individual perception, collaborative perception has been proposed which enables vehicles to share information to perceive the environments beyond line-of-sight and field-of-view. In this paper, we provide a review of the related work about the promising collaborative perception technology, including introducing the fundamental concepts, generalizing the collaboration modes and summarizing the key ingredients and applications of collaborative perception. Finally, we discuss the open challenges and issues of this research area and give some potential further directions.
3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate multiview feature by sampling regular 3D grid densely in space, which is inefficient. In this paper, we attempt to improve multi-view feature aggregation by proposing a learnable keypoints sampling method, which scatters pseudo surface points in 3D space, in order to keep data sparsity. The scattered points augmented by multi-view geometric constraints and visual features are then employed to infer objects location and shape in the scene. To make up the limitations of single frame and model multi-view geometry explicitly, we further propose a surface filter module for noise suppression. Experimental results show that our method achieves significantly better performance than previous works in terms of 3D detection (more than 0.1 AP improvement on some categories of ScanNet). The code will be publicly available.
Computed Tomography (CT) is an imaging technique where information about an object are collected at different angles (called projections or scans). Then the cross-sectional image showing the internal structure of the slice is produced by solving an inverse problem. Limited by certain factors such as radiation dosage, projection angles, the produced images can be noisy or contain artifacts. Inspired by the success of transformer for natural language processing, the core idea of this preliminary study is to consider a projection of tomography as a word token, and the whole scan of the cross-section (A.K.A. sinogram) as a sentence in the context of natural language processing. Then we explore the idea of foundation model by training a masked sinogram model (MSM) and fine-tune MSM for various downstream applications including CT reconstruction under data collections restriction (e.g., photon-budget) and a data-driven solution to approximate solutions of the inverse problem for CT reconstruction. Models and data used in this study are available at https://github.com/lzhengchun/TomoTx.
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human inspection, it is essential that the injected data appear to be correctly labeled. The attacks with such property are often referred to as "clean-label attacks." Existing clean-label backdoor attacks require knowledge of the entire training set to be effective. Obtaining such knowledge is difficult or impossible because training data are often gathered from multiple sources (e.g., face images from different users). It remains a question whether backdoor attacks still present a real threat. This paper provides an affirmative answer to this question by designing an algorithm to mount clean-label backdoor attacks based only on the knowledge of representative examples from the target class. With poisoning equal to or less than 0.5% of the target-class data and 0.05% of the training set, we can train a model to classify test examples from arbitrary classes into the target class when the examples are patched with a backdoor trigger. Our attack works well across datasets and models, even when the trigger presents in the physical world. We explore the space of defenses and find that, surprisingly, our attack can evade the latest state-of-the-art defenses in their vanilla form, or after a simple twist, we can adapt to the downstream defenses. We study the cause of the intriguing effectiveness and find that because the trigger synthesized by our attack contains features as persistent as the original semantic features of the target class, any attempt to remove such triggers would inevitably hurt the model accuracy first.
In recent years, graph neural networks (GNNs) combined with variants of recurrent neural networks (RNNs) have reached state-of-the-art performance in spatiotemporal forecasting tasks. This is particularly the case for traffic forecasting, where GNN models use the graph structure of road networks to account for spatial correlation between links and nodes. Recent solutions are either based on complex graph operations or avoiding predefined graphs. This paper proposes a new sequence-to-sequence architecture to extract the spatiotemporal correlation at multiple levels of abstraction using GNN-RNN cells with sparse architecture to decrease training time compared to more complex designs. Encoding the same input sequence through multiple encoders, with an incremental increase in encoder layers, enables the network to learn general and detailed information through multilevel abstraction. We further present a new benchmark dataset of street-level segment traffic data from Montreal, Canada. Unlike highways, urban road segments are cyclic and characterized by complicated spatial dependencies. Experimental results on the METR-LA benchmark highway and our MSLTD street-level segment datasets demonstrate that our model improves performance by more than 7% for one-hour prediction compared to the baseline methods while reducing computing resource requirements by more than half compared to other competing methods.
Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines.
Recommendation systems have been widely used in various domains such as music, films, e-shopping etc. After mostly avoiding digitization, the art world has recently reached a technological turning point due to the pandemic, making online sales grow significantly as well as providing quantitative online data about artists and artworks. In this work, we present a content-based recommendation system on contemporary art relying on images of artworks and contextual metadata of artists. We gathered and annotated artworks with advanced and art-specific information to create a completely unique database that was used to train our models. With this information, we built a proximity graph between artworks. Similarly, we used NLP techniques to characterize the practices of the artists and we extracted information from exhibitions and other event history to create a proximity graph between artists. The power of graph analysis enables us to provide an artwork recommendation system based on a combination of visual and contextual information from artworks and artists. After an assessment by a team of art specialists, we get an average final rating of 75% of meaningful artworks when compared to their professional evaluations.
With the development of machine learning techniques, the attention of research has been moved from single-modal learning to multi-modal learning, as real-world data exist in the form of different modalities. However, multi-modal models often carry more information than single-modal models and they are usually applied in sensitive scenarios, such as medical report generation or disease identification. Compared with the existing membership inference against machine learning classifiers, we focus on the problem that the input and output of the multi-modal models are in different modalities, such as image captioning. This work studies the privacy leakage of multi-modal models through the lens of membership inference attack, a process of determining whether a data record involves in the model training process or not. To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively. More specifically, MB M^4I adopts similarity metrics while attacking to infer target data membership. FB M^4I uses a pre-trained shadow multi-modal feature extractor to achieve the purpose of data inference attack by comparing the similarities from extracted input and output features. Extensive experimental results show that both attack methods can achieve strong performances. Respectively, 72.5% and 94.83% of attack success rates on average can be obtained under unrestricted scenarios. Moreover, we evaluate multiple defense mechanisms against our attacks. The source code of M^4I attacks is publicly available at https://github.com/MultimodalMI/Multimodal-membership-inference.git.