CGBA: Curvature-aware Geometric Black-box Attack

Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction often suffer from inefficiency and convergence issues. In this paper, we propose a novel query-efficient curvature-aware geometric decision-based black-box attack (CGBA) that conducts boundary search along a semicircular path on a restricted 2D plane to ensure finding a boundary point successfully irrespective of the boundary curvature. While the proposed CGBA attack can work effectively for an arbitrary decision boundary, it is particularly efficient in exploiting the low curvature to craft high-quality adversarial examples, which is widely seen and experimentally verified in commonly used classifiers under non-targeted attacks. In contrast, the decision boundaries often exhibit higher curvature under targeted attacks. Thus, we develop a new query-efficient variant, CGBA-H, that is adapted for the targeted attack. In addition, we further design an algorithm to obtain a better initial boundary point at the expense of some extra queries, which considerably enhances the performance of the targeted attack. Extensive experiments are conducted to evaluate the performance of our proposed methods against some well-known classifiers on the ImageNet and CIFAR10 datasets, demonstrating the superiority of CGBA and CGBA-H over state-of-the-art non-targeted and targeted attacks, respectively. The source code is available at https://github.com/Farhamdur/CGBA.

Volumetric Wireframe Parsing from Neural Attraction Fields

The primal sketch is a fundamental representation in Marr's vision theory, which allows for parsimonious image-level processing from 2D to 2.5D perception. This paper takes a further step by computing 3D primal sketch of wireframes from a set of images with known camera poses, in which we take the 2D wireframes in multi-view images as the basis to compute 3D wireframes in a volumetric rendering formulation. In our method, we first propose a NEural Attraction (NEAT) Fields that parameterizes the 3D line segments with coordinate Multi-Layer Perceptrons (MLPs), enabling us to learn the 3D line segments from 2D observation without incurring any explicit feature correspondences across views. We then present a novel Global Junction Perceiving (GJP) module to perceive meaningful 3D junctions from the NEAT Fields of 3D line segments by optimizing a randomly initialized high-dimensional latent array and a lightweight decoding MLP. Benefitting from our explicit modeling of 3D junctions, we finally compute the primal sketch of 3D wireframes by attracting the queried 3D line segments to the 3D junctions, significantly simplifying the computation paradigm of 3D wireframe parsing. In experiments, we evaluate our approach on the DTU and BlendedMVS datasets with promising performance obtained. As far as we know, our method is the first approach to achieve high-fidelity 3D wireframe parsing without requiring explicit matching.

Implicit Bayes Adaptation: A Collaborative Transport Approach

The power and flexibility of Optimal Transport (OT) have pervaded a wide spectrum of problems, including recent Machine Learning challenges such as unsupervised domain adaptation. Its essence of quantitatively relating two probability distributions by some optimal metric, has been creatively exploited and shown to hold promise for many real-world data challenges. In a related theme in the present work, we posit that domain adaptation robustness is rooted in the intrinsic (latent) representations of the respective data, which are inherently lying in a non-linear submanifold embedded in a higher dimensional Euclidean space. We account for the geometric properties by refining the $l^2$ Euclidean metric to better reflect the geodesic distance between two distinct representations. We integrate a metric correction term as well as a prior cluster structure in the source data of the OT-driven adaptation. We show that this is tantamount to an implicit Bayesian framework, which we demonstrate to be viable for a more robust and better-performing approach to domain adaptation. Substantiating experiments are also included for validation purposes.

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner. Specifically, we first obtain initial proposals from off-the-shelf backbone monocular 3D detectors. Then, we generate a 3D anchor space by local-grid sampling from the initial proposals. Finally, we perform 3D bounding box denoising at the 3D-to-2D proposal verification stage. To effectively learn discriminative features for denoising highly overlapped proposals, this paper presents a method of using the Perceiver I/O model to fuse the 3D-to-2D geometric information and the 2D appearance information. With the encoded latent representation of a proposal, the verification head is implemented with a self-attention module. Our method, named as MonoXiver, is generic and can be easily adapted to any backbone monocular 3D detectors. Experimental results on the well-established KITTI dataset and the challenging large-scale Waymo dataset show that MonoXiver consistently achieves improvement with limited computation overhead.

Learning to Grow Artificial Hippocampi in Vision Transformers for Resilient Lifelong Learning

Lifelong learning without catastrophic forgetting (i.e., resiliency) possessed by human intelligence is entangled with sophisticated memory mechanisms in the brain, especially the long-term memory (LM) maintained by Hippocampi. To a certain extent, Transformers have emerged as the counterpart ``Brain" of Artificial Intelligence (AI), and yet leave the LM component under-explored for lifelong learning settings. This paper presents a method of learning to grow Artificial Hippocampi (ArtiHippo) in Vision Transformers (ViTs) for resilient lifelong learning. With a comprehensive ablation study, the final linear projection layer in the multi-head self-attention (MHSA) block is selected in realizing and growing ArtiHippo. ArtiHippo is represented by a mixture of experts (MoEs). Each expert component is an on-site variant of the linear projection layer, maintained via neural architecture search (NAS) with the search space defined by four basic growing operations -- skip, reuse, adapt, and new in lifelong learning. The LM of a task consists of two parts: the dedicated expert components (as model parameters) at different layers of a ViT learned via NAS, and the mean class-tokens (as stored latent vectors for measuring task similarity) associated with the expert components. For a new task, a hierarchical task-similarity-oriented exploration-exploitation sampling based NAS is proposed to learn the expert components. The task similarity is measured based on the normalized cosine similarity between the mean class-token of the new task and those of old tasks. The proposed method is complementary to prompt-based lifelong learningwith ViTs. In experiments, the proposed method is tested on the challenging Visual Domain Decathlon (VDD) benchmark and the recently proposed 5-Dataset benchmark. It obtains consistently better performance than the prior art with sensible ArtiHippo learned continually.

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation. We present a novel Neural One-PlanE RANSAC framework (termed NOPE-SAC in short) that exerts excellent capability to learn one-plane pose hypotheses from 3D plane correspondences. Building on the top of a siamese plane detection network, our NOPE-SAC first generates putative plane correspondences with a coarse initial pose. It then feeds the learned 3D plane parameters of correspondences into shared MLPs to estimate the one-plane camera pose hypotheses, which are subsequently reweighed in a RANSAC manner to obtain the final camera pose. Because the neural one-plane pose minimizes the number of plane correspondences for adaptive pose hypotheses generation, it enables stable pose voting and reliable pose refinement in a few plane correspondences for the sparse-view inputs. In the experiments, we demonstrate that our NOPE-SAC significantly improves the camera pose estimation for the two-view inputs with severe viewpoint changes, setting several new state-of-the-art performances on two challenging benchmarks, i.e., MatterPort3D and ScanNet, for sparse-view 3D reconstruction. The source code is released at https://github.com/IceTTTb/NopeSAC for reproducible research.

Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM. In our formulation, we aim at simultaneously learning coordinate MLPs for the implicit surfaces and the radiance fields, and estimating the camera poses and scene geometry, which is mainly sourced from the established keypoint correspondences by SIFT. Our formulation would face some new challenges due to inevitable two-view and few-view configurations at the beginning of incremental SfM pipeline for the optimization of coordinate MLPs, but we found that the strong inductive biases conveying in the 2D correspondences are feasible and promising to avoid those challenges by exploiting the relationship between the ray sampling schemes used in volumetric rendering and the sphere tracing of finding the zero-level set of implicit surfaces. Based on this, we revisit the pipeline of incremental SfM and renew the key components of two-view geometry initialization, the camera pose registration, and the 3D points triangulation, as well as the Bundle Adjustment in a novel perspective of neural implicit surfaces. Because the coordinate MLPs unified the scene geometry in small MLP networks, our Level-S$^2$fM treats the zero-level set of the implicit surface as an informative top-down regularization to manage the reconstructed 3D points, reject the outlier of correspondences by querying SDF, adjust the estimated geometries by NBA (Neural BA), finally yielding promising results of 3D reconstruction. Furthermore, our Level-S$^2$fM alleviated the requirement of camera poses for neural 3D reconstruction.

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

This paper presents Holistically-Attracted Wireframe Parsing (HAWP) for 2D images using both fully supervised and self-supervised learning paradigms. At the core is a parsimonious representation that encodes a line segment using a closed-form 4D geometric vector, which enables lifting line segments in wireframe to an end-to-end trainable holistic attraction field that has built-in geometry-awareness, context-awareness and robustness. The proposed HAWP consists of three components: generating line segment and end-point proposal, binding line segment and end-point, and end-point-decoupled lines-of-interest verification. For self-supervised learning, a simulation-to-reality pipeline is exploited in which a HAWP is first trained using synthetic data and then used to ``annotate" wireframes in real images with Homographic Adaptation. With the self-supervised annotations, a HAWP model for real images is trained from scratch. In experiments, the proposed HAWP achieves state-of-the-art performance in both the Wireframe dataset and the YorkUrban dataset in fully-supervised learning. It also demonstrates a significantly better repeatability score than prior arts with much more efficient training in self-supervised learning. Furthermore, the self-supervised HAWP shows great potential for general wireframe parsing without onerous wireframe labels.

HoW-3D: Holistic 3D Wireframe Perception from a Single Image

This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images. As the non-front surfaces of an object cannot be directly observed in a single view, estimating the non-line-of-sight (NLOS) geometries in HoW-3D is a fundamentally challenging problem and remains open in computer vision. We study the problem of HoW-3D by proposing an ABC-HoW benchmark, which is created on top of CAD models sourced from the ABC-dataset with 12k single-view images and the corresponding holistic 3D wireframe models. With our large-scale ABC-HoW benchmark available, we present a novel Deep Spatial Gestalt (DSG) model to learn the visible junctions and line segments as the basis and then infer the NLOS 3D structures from the visible cues by following the Gestalt principles of human vision systems. In our experiments, we demonstrate that our DSG model performs very well in inferring the holistic 3D wireframes from single-view images. Compared with the strong baseline methods, our DSG model outperforms the previous wireframe detectors in detecting the invisible line geometry in single-view images and is even very competitive with prior arts that take high-fidelity PointCloud as inputs on reconstructing 3D wireframes.

Learning Patch-to-Cluster Attention in Vision Transformer

The Vision Transformer (ViT) model is built on the assumption of treating image patches as "visual tokens" and learning patch-to-patch attention. The patch embedding based tokenizer is a workaround in practice and has a semantic gap with respect to its counterpart, the textual tokenizer. The patch-to-patch attention suffers from the quadratic complexity issue, and also makes it non-trivial to explain learned ViT models. To address these issues in ViT models, this paper proposes to learn patch-to-cluster attention (PaCa) based ViT models. Queries in our PaCaViT are based on patches, while keys and values are based on clustering (with a predefined small number of clusters). The clusters are learned end-to-end, leading to better tokenizers and realizing joint clustering-for-attention and attention-for-clustering when deployed in ViT models. The quadratic complexity is relaxed to linear complexity. Also, directly visualizing the learned clusters can reveal how a trained ViT model learns to perform a task (e.g., object detection). In experiments, the proposed PaCa-ViT is tested on CIFAR-100 and ImageNet-1000 image classification, and MS-COCO object detection and instance segmentation. Compared with prior arts, it obtains better performance in classification and comparable performance in detection and segmentation. It is significantly more efficient in COCO due to the linear complexity. The learned clusters are also semantically meaningful and shed light on designing more discriminative yet interpretable ViT models.