Multi-view projection methods have shown the capability to reach state-of-the-art performance on 3D shape recognition. Most advances in multi-view representation focus on pooling techniques that learn to aggregate information from the different views, which tend to be heuristically set and fixed for all shapes. To circumvent the lack of dynamism of current multi-view methods, we propose to learn those viewpoints. In particular, we introduce a Multi-View Transformation Network (MVTN) that regresses optimal viewpoints for 3D shape recognition. By leveraging advances in differentiable rendering, our MVTN is trained end-to-end with any multi-view network and optimized for 3D shape classification. We show that MVTN can be seamlessly integrated into various multi-view approaches to exhibit clear performance gains in the tasks of 3D shape classification and shape retrieval without any extra training supervision. Furthermore, our MVTN improves multi-view networks to achieve state-of-the-art performance in rotation robustness and in object shape retrieval on ModelNet40.
Point cloud architecture design has become a crucial problem for 3D deep learning. Several efforts exist to manually design architectures with high accuracy in point cloud tasks such as classification, segmentation, and detection. Recent progress in automatic Neural Architecture Search (NAS) minimizes the human effort in network design and optimizes high performing architectures. However, these efforts fail to consider important factors such as latency during inference. Latency is of high importance in time critical applications like self-driving cars, robot navigation, and mobile applications, that are generally bound by the available hardware. In this paper, we introduce a new NAS framework, dubbed LC-NAS, where we search for point cloud architectures that are constrained to a target latency. We implement a novel latency constraint formulation to trade-off between accuracy and latency in our architecture search. Contrary to previous works, our latency loss guarantees that the final network achieves latency under a specified target value. This is crucial when the end task is to be deployed in a limited hardware setting. Extensive experiments show that LC-NAS is able to find state-of-the-art architectures for point cloud classification in ModelNet40 with minimal computational cost. We also show how our searched architectures achieve any desired latency with a reasonably low drop in accuracy. Finally, we show how our searched architectures easily transfer to a different task, part segmentation on PartNet, where we achieve state-of-the-art results while lowering latency by a factor of 10.
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to correlate with human perception. Inspired by this connection from robustness to semantics, we study the complementary connection: from semantics to robustness. To do so, we provide a tight robustness certificate for distance-based classification models (clustering-based classifiers), which we leverage to propose ClusTR (Clustering Training for Robustness), a clustering-based and adversary-free training framework to learn robust models. Interestingly, ClusTR outperforms adversarially-trained networks by up to 4\% under strong PGD attacks. Moreover, it can be equipped with simple and fast adversarial training to improve the current state-of-the-art in robustness by 16\%-29\% on CIFAR10, SVHN, and CIFAR100.
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Unlike Convolutional Neural Networks (CNNs), which are able to take advantage of stacking very deep layers, GCNs suffer from vanishing gradient, over-smoothing and over-fitting issues when going deeper. These challenges limit the representation power of GCNs on large-scale graphs. This paper proposes DeeperGCN that is capable of successfully and reliably training very deep GCNs. We define differentiable generalized aggregation functions to unify different message aggregation operations (e.g. mean, max). We also propose a novel normalization layer namely MsgNorm and a pre-activation version of residual connections for GCNs. Extensive experiments on Open Graph Benchmark (OGB) show DeeperGCN significantly boosts performance over the state-of-the-art on the large scale graph learning tasks of node property prediction and graph property prediction. Please visit https://www.deepgcns.org for more information.
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to correlate with human perception. Inspired by this connection from robustness to semantics, we study the complementary connection: from semantics to robustness. To do so, we provide a tight robustness certificate for distance-based classification models (clustering-based classifiers), which we leverage to propose \emph{ClusTR} (Clustering Training for Robustness), a clustering-based and adversary-free training framework to learn robust models. Interestingly, \textit{ClusTR} outperforms adversarially-trained networks by up to $4\%$ under strong PGD attacks. Moreover, it can be equipped with simple and fast adversarial training to improve the current state-of-the-art in robustness by $16\%$-$29\%$ on CIFAR10, SVHN, and CIFAR100.
This work takes a step towards investigating the benefits of merging classical vision techniques with deep learning models. Formally, we explore the effect of replacing the first layers of neural network architectures with convolutional layers that are based on Gabor filters with learnable parameters. As a first result, we observe that architectures utilizing Gabor filters as low-level kernels are capable of preserving test set accuracy of deep convolutional networks. Therefore, this architectural change exalts their capabilities in extracting useful low-level features. Furthermore, we observe that the architectures enhanced with Gabor layers gain advantages in terms of robustness when compared to the regular models. Additionally, the existence of a closed mathematical expression for the Gabor kernels allows us to develop an analytical expression for an upper bound to the Lipschitz constant of the Gabor layer. This expression allows us to propose a simple regularizer to enhance the robustness of the network. We conduct extensive experiments with several architectures and datasets, and show the beneficial effects that the introduction of Gabor layers has on the robustness of deep convolutional networks.
Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been extensively studied in the image domain, and only recently extended to 3D point clouds. In this work, we present novel data-driven adversarial attacks against 3D point cloud networks. We aim to address the following problems in current 3D point cloud adversarial attacks: they do not transfer well between different networks, and they are easy to defend against simple statistical methods. To this extent, we develop new point cloud attacks (we dub AdvPC) that exploit input data distributions. These attacks lead to perturbations that are resilient against current defenses while remaining highly transferable compared to state-of-the-art attacks. We test our attacks using four popular point cloud networks: PointNet, PointNet++ (MSG and SSG), and DGCNN. Our proposed attack enables an increase in the transferability of up to 20 points for some networks. It also increases the ability to break defenses of up to 23 points on ModelNet40 data.
Upsampling sparse, noisy, and non-uniform point clouds is a challenging task. In this paper, we propose 3 novel point upsampling modules: Multi-branch GCN, Clone GCN, and NodeShuffle. Our modules use Graph Convolutional Networks (GCNs) to better encode local point information. Our upsampling modules are versatile and can be incorporated into any point cloud upsampling pipeline. We show how our 3 modules consistently improve state-of-the-art methods in all point upsampling metrics. We also propose a new multi-scale point feature extractor, called Inception DenseGCN. We modify current Inception GCN algorithms by introducing DenseGCN blocks. By aggregating data at multiple scales, our new feature extractor is more resilient to density changes along point cloud surfaces. We combine Inception DenseGCN with one of our upsampling modules (NodeShuffle) into a new point upsampling pipeline: PU-GCN. We show both qualitatively and quantitatively the advantages of PU-GCN against the state-of-the-art in terms of fine-grained upsampling quality and point cloud uniformity. The website and source code of this work is available at https://sites.google.com/kaust.edu.sa/pugcn and https://github.com/guochengqian/PU-GCN respectively.
Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy during the search phase may perform worse in the evaluation. Aiming to alleviate this common issue, we introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost. Please visit https://sites.google.com/kaust.edu.sa/sgas for more information about SGAS.
Temporal action detection is a fundamental yet challenging task in video understanding. Video context is a critical cue to effectively detect actions, but current works mainly focus on temporal context, while neglecting semantic con-text as well as other important context properties. In this work, we propose a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem. Specifically, we formulate video snippets as graph nodes, snippet-snippet cor-relations as edges, and actions associated with context as target sub-graphs. With graph convolution as the basic operation, we design a GCN block called GCNeXt, which learns the features of each node by aggregating its context and dynamically updates the edges in the graph. To localize each sub-graph, we also design a SGAlign layer to embed each sub-graph into the Euclidean space. Extensive experiments show that G-TAD is capable of finding effective video context without extra supervision and achieves state-of-the-art performance on two detection benchmarks. On ActityNet-1.3, we obtain an average mAP of 34.09%; on THUMOS14, we obtain 40.16% in mAP@0.5, beating all the other one-stage methods.