-
Chapter and Conference Paper
Adversarial Geometric Transformations of Point Clouds for Physical Attack
Towards adversarial physical attack in real world, we argue that the main challenge lies in discounting adversarial effects by changes of point density along object surface. Most of existing point-wise perturb...
-
Chapter and Conference Paper
Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks
It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e.g., category-level 6D object pose and size estimation...
-
Chapter and Conference Paper
Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers
Semi-supervised learning (SSL) has achieved new progress recently with the emerging framework of self-training deep networks, where the criteria for selection of unlabeled samples with pseudo labels play a key...
-
Chapter and Conference Paper
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic ...
-
Chapter and Conference Paper
DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence learning in 3D space are a step a...
-
Chapter and Conference Paper
Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities. Existing methods strive to organize the points regularly, e.g. voxelize, pass them thro...
-
Chapter and Conference Paper
Label Propagation with Augmented Anchors: A Simple Semi-supervised Learning Baseline for Unsupervised Domain Adaptation
Motivated by the problem relatedness between unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), many state-of-the-art UDA methods adopt SSL principles (e.g., the cluster assumption) as th...
-
Chapter and Conference Paper
Fine-Grained Visual Categorization Using Meta-learning Optimization with Sample Selection of Auxiliary Data
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering fr...
-
Article
ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images
Feature-based object matching is a fundamental problem for many applications in computer vision, such as object recognition, 3D reconstruction, tracking, and motion segmentation. In this work, we consider simu...
-
Article
Neither Global Nor Local: Regularized Patch-Based Representation for Single Sample Per Person Face Recognition
This paper presents a regularized patch-based representation for single sample per person face recognition. We represent each image by a collection of patches and seek their sparse representations under the ga...
-
Chapter and Conference Paper
Finding Correspondence from Multiple Images via Sparse and Low-Rank Decomposition
We investigate the problem of finding the correspondence from multiple images, which is a challenging combinatorial problem. In this work, we propose a robust solution by exploiting the priors that the rank of...
-
Chapter and Conference Paper
Towards Optimal Design of Time and Color Multiplexing Codes
Multiplexed illumination has been proved to be valuable and beneficial, in terms of noise reduction, in wide applications of computer vision and graphics, provided that the limitations of photon noise and satu...