Search Results for author:
Found 40 papers, 21 papers with code
Region Graph Embedding Network for Zero-Shot Learning
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
Learning Attentive and Hierarchical Representations for 3D Shape Recognition
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
Visual-Tactile Sensing for Real-time Liquid Volume Estimation in Grasping
We propose a deep visuo-tactile model for realtime estimation of the liquid inside a deformable container in a proprioceptive way. We fuse two sensory modalities, i. e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrations. The robotic system is well controlled and adjusted based on the estimation model in real time.
Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.
G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.
A LiDAR Assisted Control Module with High Precision in Parking Scenarios for Autonomous Driving Vehicle
For example, humans are good at interactive tasks (while autonomous driving systems usually do not), but we are often incompetent for tasks with strict precision demands.
Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.
Ranked #6 on
Person Re-Identification
on iLIDS-VID
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
Anchor-Free Person Search
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #10 on
Person Search
on CUHK-SYSU
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds.
Group Whitening: Balancing Learning Efficiency and Representational Capacity
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.
Ranked #69 on
Semantic Segmentation
on ADE20K val
Improved Residual Networks for Image and Video Recognition
We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths.
Controllable Orthogonalization in Training DNNs
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.
An Investigation into the Stochasticity of Batch Whitening
Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).
Auto-Encoding Twin-Bottleneck Hashing
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent
Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning.
Embarrassingly Simple Binary Representation Learning
Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries.
RANet: Ranking Attention Network for Fast Video Object Segmentation
Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner.
Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.
NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoising
This is motivated by the fact that finding closely similar pixels is more feasible than similar patches in natural images, which can be used to enhance image denoising performance.
STAR: A Structure and Texture Aware Retinex Model
A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image.
Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset
Firstly, since document image quality assessment is more interested in text, we propose a text line based framework to estimate document image quality, which is composed of three stages: text line detection, text line quality prediction, and overall quality assessment.
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances.
Ranked #1 on
Object Detection
on iSAID
Dynamically Visual Disambiguation of Keyword-based Image Search
To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation.
Iterative Normalization: Beyond Standardization towards Efficient Whitening
With the support of SND, we provide natural explanations to several phenomena from the perspective of optimization, e. g., why group-wise whitening of DBN generally outperforms full-whitening and why the accuracy of BN degenerates with reduced batch sizes.
Ranked #8 on
Robust Object Detection
on DWD
Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
How to economically cluster large-scale multi-view images is a long-standing problem in computer vision.
TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights
Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e. g., portable or smart wearable devices).
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability.
Baidu Apollo Auto-Calibration System - An Industry-Level Data-Driven and Learning based Vehicle Longitude Dynamic Calibrating Algorithm
Since manual calibration is not sustainable once entering into mass production stage for industrial purposes, we here introduce a machine-learning based auto-calibration system for autonomous driving vehicles.
Baidu Apollo EM Motion Planner
In this manuscript, we introduce a real-time motion planning system based on the Baidu Apollo (open source) autonomous driving platform.
CG-DIQA: No-reference Document Image Quality Assessment Based on Character Gradient
Document image quality assessment (DIQA) is an important and challenging problem in real applications.
Image Quality Assessment
Optical Character Recognition (OCR)
Towards Automatic Construction of Diverse, High-quality Image Dataset
To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries.
Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval
For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation.
3D Deep Shape Descriptor
Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category.
DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval
Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning.
Submodular Object Recognition
We present a novel object recognition framework based on multiple figure-ground hypotheses with a large object spatial support, generated by bottom-up processes and mid-level cues in an unsupervised manner.
