
Learning to Reconstruct 3D NonCuboid Room Layout from a Single RGB Image
Singleimage room layout reconstruction aims to reconstruct the enclosed...
read it

Understanding Generalization in Adversarial Training via the BiasVariance Decomposition
Adversarially trained models exhibit a large generalization gap: they ca...
read it

Optimistic Dual Extrapolation for Coherent Nonmonotone Variational Inequalities
The optimization problems associated with training generative adversaria...
read it

Incremental Learning via Rate Reduction
Current deep learning architectures suffer from catastrophic forgetting,...
read it

Deep Networks from the Principle of Rate Reduction
This work attempts to interpret modern deep (convolutional) networks fro...
read it

HoliCity: A CityScale Data Platform for Learning Holistic 3D Structures
We present HoliCity, a cityscale 3D dataset with rich structural inform...
read it

Learning Longterm Visual Dynamics with Region Proposal Interaction Networks
Learning longterm dynamics models is the key to understanding physical ...
read it

Learning to Parse Wireframes in Images of ManMade Environments
In this paper, we propose a learningbased approach to the task of autom...
read it

Deep Isometric Learning for Visual Recognition
Initialization, normalization, and skip connections are believed to be t...
read it

Dynamic Knapsack Optimization Towards Efficient MultiChannel Sequential Advertising
In Ecommerce, advertising is essential for merchants to reach their tar...
read it

Stochastic Variance Reduction via Accelerated Dual Averaging for FiniteSum Optimization
In this paper, we introduce a simplified and unified method for finites...
read it

Learning to Detect 3D Reflection Symmetry for SingleView Reconstruction
3D reconstruction from a single RGB image is a challenging problem in co...
read it

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Overparameterization
Recent advances have shown that implicit bias of gradient descent on ove...
read it

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
To learn intrinsic lowdimensional structures from highdimensional data...
read it

Learning to Accelerate Heuristic Searching for LargeScale Maximum Weighted bMatching Problems in Online Advertising
Bipartite bmatching is fundamental in algorithm design, and has been wi...
read it

On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MUMIMO Systems
This paper aims to handle the joint transmitter and noncoherent receiver...
read it

A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
In this paper, we reveal that artificial neural network (ANN) assisted m...
read it

Rethinking BiasVariance Tradeoff for Generalization of Neural Networks
The classical biasvariance tradeoff predicts that bias decreases and v...
read it

KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
Reinforcement learning agents usually learn from scratch, which requires...
read it

An ActorCriticBased UAVBSs Deployment Method for Dynamic Environments
In this paper, the realtime deployment of unmanned aerial vehicles (UAV...
read it

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
We present a simple yet effective endtoend trainable deep network with...
read it

Spectralbased Graph Convolutional Network for Directed Graphs
Graph convolutional networks(GCNs) have become the most popular approach...
read it

Complete Dictionary Learning via ℓ^4Norm Maximization over the Orthogonal Group
This paper considers the fundamental problem of learning a complete (ort...
read it

Towards Unified Acceleration of HighOrder Algorithms under Hölder Continuity and Uniform Convexity
In this paper, through a very intuitive vanilla proximal method perspec...
read it

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
In this paper, we propose a method to obtain a compact and accurate 3D w...
read it

EndtoEnd Wireframe Parsing
We present a conceptually simple yet effective algorithm to detect wiref...
read it

Finegrained Video Categorization with Redundancy Reduction Attention
For finegrained categorization tasks, videos could serve as a better so...
read it

TARM: A Turbotype Algorithm for Affine Rank Minimization
The affine rank minimization (ARM) problem arises in many realworld app...
read it

SymbolLevel Selective FullDuplex Relaying with Power and Location Optimization
In this paper, a symbollevel selective transmission for fullduplex (FD...
read it

Structured Attentions for Visual Question Answering
Visual attention, which assigns weights to image regions according to th...
read it

Graph Construction with Label Information for SemiSupervised Learning
In the literature, most existing graphbased semisupervised learning (S...
read it

Automatic Layer Separation using Light Field Imaging
We propose a novel approach that jointly removes reflection or transluce...
read it

Robust Face Recognition by Constrained Partbased Alignment
Developing a reliable and practical face recognition system is a longst...
read it

Constructing a NonNegative Low Rank and Sparse Graph with DataAdaptive Features
This paper aims at constructing a good graph for discovering intrinsic d...
read it

PCANet: A Simple Deep Learning Baseline for Image Classification?
In this work, we propose a very simple deep learning network for image c...
read it

Sparse Illumination Learning and Transfer for SingleSample Face Recognition with Image Corruption and Misalignment
Singlesample face recognition is one of the most challenging problems i...
read it

Blind Image Deblurring by Spectral Properties of Convolution Operators
In this paper, we study the problem of recovering a sharp version of a g...
read it

Sparsity and Robustness in Face Recognition
This report concerns the use of techniques for sparse signal representat...
read it

TILT: Transform Invariant Lowrank Textures
In this paper, we show how to efficiently and effectively extract a clas...
read it

Robust Recovery of Subspace Structures by LowRank Representation
In this work we address the subspace recovery problem. Given a set of da...
read it

Fast L1Minimization Algorithms For Robust Face Recognition
L1minimization refers to finding the minimum L1norm solution to an und...
read it

Segmentation of Natural Images by Texture and Boundary Compression
We present a novel algorithm for segmentation of natural images that har...
read it
Yi Ma
is this you? claim profile
Department of Electrical Engineering and Computer Sciences at University of California at Berkeley