Search Results for author:
Found 49 papers, 16 papers with code
Textual Representations for Crosslingual Information Retrieval
In this paper, we explored different levels of textual representations for cross-lingual information retrieval.
Optimal Estimator for Unlabeled Linear Regression
Unlabeled linear regression, or ``linear regression with an unknown permutation'', has attracted increasing attentions due to its applications in linkage record and de-anonymization.
Structure Learning in Graphical Models from Indirect Observations
For the first time, we show that the correct graphical structure can be correctly recovered under the indefinite sensing system ($d < p$) using insufficient samples ($n < p$).
A General Compressive Sensing Construct using Density Evolution
This paper proposes a general framework to design a sparse sensing matrix $\ensuremath{\mathbf{A}}\in \mathbb{R}^{m\times n}$, in a linear measurement system $\ensuremath{\mathbf{y}} = \ensuremath{\mathbf{Ax}}^{\natural} + \ensuremath{\mathbf{w}}$, where $\ensuremath{\mathbf{y}} \in \mathbb{R}^m$, $\ensuremath{\mathbf{x}}^{\natural}\in \RR^n$, and $\ensuremath{\mathbf{w}}$ denote the measurements, the signal with certain structures, and the measurement noise, respectively.
Design of Compressed Sensing Systems via Density-Evolution Framework for Structure Recovery in Graphical Models
In particular, under the assumption that both the covariance matrix and the graph are sparse, we show that the structure of GBN can indeed be recovered from resulting compressed measurements.
Online Dynamic Parameter Estimation of an Alkaline Electrolysis System Based on Bayesian Inference
When directly coupled with fluctuating energy sources such as wind and photovoltage power, the alkaline electrolysis (AEL) in a power-to-hydrogen (P2H) system is required to operate flexibly by dynamically adjusting its hydrogen production rate.
Unified smoke and fire detection in an evolutionary framework with self-supervised progressive data augment
Few researches have studied simultaneous detection of smoke and flame accompanying fires due to their different physical natures that lead to uncertain fluid patterns.
CodeRetriever: Unimodal and Bimodal Contrastive Learning
For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build text-code pairs.
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
To tackle these challenges, we propose FBNetV5, a NAS framework that can search for neural architectures for a variety of vision tasks with much reduced computational cost and human effort.
Ranked #87 on
Semantic Segmentation
on ADE20K
Adversarial Retriever-Ranker for dense text retrieval
The two models are jointly optimized according to a minimax adversarial objective: the retriever learns to retrieve negative documents to cheat the ranker, while the ranker learns to rank a collection of candidates including both the ground-truth and the retrieved ones, as well as providing progressive direct feedback to the dual-encoder retriever.
An Investigation on Hardware-Aware Vision Transformer Scaling
In particular, when transferred to PiT, our scaling strategies lead to a boosted ImageNet top-1 accuracy of from $74. 6\%$ to $76. 7\%$ ($\uparrow2. 1\%$) under the same 0. 7G FLOPs; and when transferred to the COCO object detection task, the average precision is boosted by $\uparrow0. 7\%$ under a similar throughput on a V100 GPU.
Poolingformer: Long Document Modeling with Pooling Attention
We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA.
Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems
When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to flexibly and efficiently deal with multiple subproblems determined by weight decomposition of objectives.
Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network
An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed.
Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction
Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging.
NeRD: Neural Representation of Distribution for Medical Image Segmentation
We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.
GLGE: A New General Language Generation Evaluation Benchmark
Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP).
Ensembling Low Precision Models for Binary Biomedical Image Segmentation
Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent.
Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models.
Differential Viewpoints for Ground Terrain Material Recognition
A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition.
Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement.
Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping
A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation.
Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI
The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce the dependency on training data.
Character Matters: Video Story Understanding with Character-Aware Relations
Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots.
Improving Semantic Segmentation via Self-Training
In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.
Let's be Humorous: Knowledge Enhanced Humor Generation
To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model.
ResNeSt: Split-Attention Networks
It is well known that featuremap attention and multi-path representation are important for visual recognition.
Ranked #5 on
Instance Segmentation
on COCO test-dev
(APS metric)
FairNN- Conjoint Learning of Fair Representations for Fair Decisions
In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning.
AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file.
RSANet: Recurrent Slice-wise Attention Network for Multiple Sclerosis Lesion Segmentation
Brain lesion volume measured on T2 weighted MRI images is a clinically important disease marker in multiple sclerosis (MS).
Skull-RCNN: A CNN-based network for the skull fracture detection
Guiding by the morphological features of the skull, a skeleton-based region proposal method is proposed to make candidate boxes more concentrated in key regions and reduce invalid boxes.
The Benefits of Diversity: Permutation Recovery in Unlabeled Sensing from Multiple Measurement Vectors
For the case in which both the signal and permutation are unknown, the problem is reformulated as a bi-convex optimization problem with an auxiliary variable, which can be solved by the Alternating Direction Method of Multipliers (ADMM).
A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images
We worked with Nestle SHIELD (Skin Health, Innovation, Education, and Longevity Development, NSH) to develop a deep learning model that is able to assess acne severity from selfie images as accurate as dermatologists.
2nd Place Solution to the GQA Challenge 2019
We present a simple method that achieves unexpectedly superior performance for Complex Reasoning involved Visual Question Answering.
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Co-Occurrent Features in Semantic Segmentation
To leverage the semantic context in the co-occurrent features, we build an Aggregated Co-occurrent Feature (ACF) Module by aggregating the probability of the co-occurrent feature with the co-occurrent context.
Ranked #9 on
Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes.
Bag of Freebies for Training Object Detection Neural Networks
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}.
Blaze: Simplified High Performance Cluster Computing
We present Blaze, a C++ library that makes it easy to develop high performance parallel programs for such compute intensive tasks.
Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.
Ranked #475 on
Image Classification
on ImageNet
Deep Texture Manifold for Ground Terrain Recognition
The GTOS database (comprised of over 30, 000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition.
Context Encoding for Semantic Segmentation
In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps.
Ranked #15 on
Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Photo-realistic Facial Texture Transfer
We address the challenging problem of transferring face texture from a style face image to a content face image in a photorealistic manner without changing the identity of the original content image.
Multi-style Generative Network for Real-time Transfer
Despite the rapid progress in style transfer, existing approaches using feed-forward generative network for multi-style or arbitrary-style transfer are usually compromised of image quality and model flexibility.
Deep TEN: Texture Encoding Network
The representation is orderless and therefore is particularly useful for material and texture recognition.
Differential Angular Imaging for Material Recognition
We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement.
Robust Matrix Regression
However, in real-world applications, it is common to see the training data contaminated by noises, which can affect the robustness of these matrix regression methods.
Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
In this work, we address the question of what reflectance can reveal about materials in an efficient manner.
Reflectance Hashing for Material Recognition
Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality.
