Search Results for author:
Found 75 papers, 26 papers with code
Robust and Efficient Medical Imaging with Self-Supervision
These results suggest that REMEDIS can significantly accelerate the life-cycle of medical imaging AI development thereby presenting an important step forward for medical imaging AI to deliver broad impact.
Towards Efficient Single Image Dehazing and Desnowing
A single expert network efficiently addresses specific degradation in nasty winter scenes relying on the compact architecture and three novel components.
Towards Reliable and Explainable AI Model for Solid Pulmonary Nodule Diagnosis
However, detection and accurate diagnosis of pulmonary nodules depend heavily on the experiences of radiologists and can be a heavy workload for them.
Coarse-to-Fine Feature Mining for Video Semantic Segmentation
To address this problem, we propose a Coarse-to-Fine Feature Mining (CFFM) technique to learn a unified presentation of static contexts and motional contexts.
Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input.
Underwater Light Field Retention : Neural Rendering for Underwater Imaging
To this end, we propose a neural rendering method for underwater imaging, dubbed UWNR (Underwater Neural Rendering).
Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle
Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain, and then optimize them in a mutual learning manner by leveraging EMA and joint loss.
Zero Pixel Directional Boundary by Vector Transform
One of the key problems in boundary detection is the label representation, which typically leads to class imbalance and, as a consequence, to thick boundaries that require non-differential post-processing steps to be thinned.
LEVEN: A Large-Scale Chinese Legal Event Detection Dataset
However, existing Legal Event Detection (LED) datasets only concern incomprehensive event types and have limited annotated data, which restricts the development of LED methods and their downstream applications.
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition
This paper described the PCG-AIID system for L3DAS22 challenge in Task 1: 3D speech enhancement in office reverberant environment.
Asymptotic affirmative actions: The top trading cycles and the Boston mechanism case
This paper analyzes the asymptotic performance of two popular affirmative action policies, majority quota and minority reserve, under the top trading cycles mechanism (TTCM) and the Boston mechanism (BM).
On the Equivalence of Two Competing Affirmative Actions in School Choice
This note analyzes the outcome equivalence conditions of two popular affirmative action policies, majority quota and minority reserve, under the student optimal stable mechanism.
Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation
Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation.
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively.
Boosting Few-shot Semantic Segmentation with Transformers
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention.
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain.
P2T: Pyramid Pooling Transformer for Scene Understanding
A popular solution to this problem is to use a single pooling operation to reduce the sequence length.
Ranked #2 on
RGB Salient Object Detection
on DUTS-TE
Vision Transformers with Hierarchical Attention
This paper tackles the low-efficiency flaw of the vision transformer caused by the high computational/space complexity in Multi-Head Self-Attention (MHSA).
Boosting Crowd Counting with Transformers
This indicates that global scene context is essential, despite the seemingly bottom-up nature of the problem.
Deep learning for detecting pulmonary tuberculosis via chest radiography: an international study across 10 countries
Tuberculosis (TB) is a top-10 cause of death worldwide.
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
We develop and rigorously evaluate a deep learning based system that can accurately classify skin conditions while detecting rare conditions for which there is not enough data available for training a confident classifier.
Coarse-grained decomposition and fine-grained interaction for multi-hop question answering
Recent advances regarding question answering and reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text, requiring only single-hop reasoning.
MobileSal: Extremely Efficient RGB-D Salient Object Detection
Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD.
EDN: Salient Object Detection via Extremely-Downsampled Network
In this paper, we tap into this gap and show that enhancing high- level features is essential for SOD as well.
Predicting Prostate Cancer-Specific Mortality with A.I.-based Gleason Grading
's C-indices were 0. 87 and 0. 85 for continuous and discrete grading, respectively, compared to 0. 79 (95%CI 0. 71-0. 86) for GG obtained from the reports.
Detecting hidden signs of diabetes in external eye photographs
In validation set A (n=27, 415 patients, all undilated), the DLS detected poor blood glucose control (HbA1c > 9%) with an area under receiver operating characteristic curve (AUC) of 70. 2; moderate-or-worse DR with an AUC of 75. 3; diabetic macular edema with an AUC of 78. 0; and vision-threatening DR with an AUC of 79. 4.
Interpretable Survival Prediction for Colorectal Cancer using Deep Learning
Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features that can be reliably identified by people for future validation studies.
Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases
To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States.
DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
DARTS mainly focuses on the operation search and derives the cell topology from the operation weights.
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph.
Ranked #1 on
Image-level Supervised Instance Segmentation
on COCO test-dev
(using extra training data)
Image-level Supervised Instance Segmentation
Multiple Instance Learning
+2
Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes.
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels.
Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform
Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles, which are usually equipped with an embedded platform and have limited computational resources.
Ranked #2 on
Real-Time 3D Semantic Segmentation
on SemanticKITTI
Rethinking 3D LiDAR Point Cloud Segmentation
Many point-based semantic segmentation methods have been designed for indoor scenarios, but they struggle if they are applied to point clouds that are captured by a LiDAR sensor in an outdoor environment.
Predicting Risk of Developing Diabetic Retinopathy using Deep Learning
We created and validated two versions of a deep learning system (DLS) to predict the development of mild-or-worse ("Mild+") DR in diabetic patients undergoing DR screening.
DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality.
Ranked #3 on
Speech Enhancement
on Deep Noise Suppression (DNS) Challenge
(PESQ-NB metric)
Speech Enhancement
Audio and Speech Processing
Sound
Efficacious symmetry-adapted atomic displacement method for lattice dynamical studies
Small displacement methods have been successfully used to calculate the lattice dynamical properties of crystals.
Materials Science
Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
Using the latter training set, about 67\% of the aforementioned 48 candidates are also found, and there are 11 more new strong lensing candidates identified.
Cosmology and Nongalactic Astrophysics
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation
Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors.
Ranked #12 on
Action Segmentation
on GTEA
Rethinking Computer-Aided Tuberculosis Diagnosis
Computer-aided tuberculosis diagnosis (CTD) is a promising choice for TB diagnosis due to the great successes of deep learning.
Sub-Band Knowledge Distillation Framework for Speech Enhancement
In single-channel speech enhancement, methods based on full-band spectral features have been widely studied.
Revealing Cluster Structures Based on Mixed Sampling Frequencies
This paper proposes a new linearized mixed data sampling (MIDAS) model and develops a framework to infer clusters in a panel regression with mixed frequency data.
MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive.
Ordered or Orderless: A Revisit for Video based Person Re-Identification
Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation.
Deep learning-based survival prediction for multiple cancer types using histopathology images
Our analysis demonstrates the potential for this approach to provide prognostic information in multiple cancer types, and even within specific pathologic stages.
AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning
The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets.
Towards Disentangling Non-Robust and Robust Components in Performance Metric
Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.
A deep learning system for differential diagnosis of skin diseases
In this paper, we developed a deep learning system (DLS) to provide a differential diagnosis of skin conditions for clinical cases (skin photographs and associated medical histories).
An Evaluation of Feature Matchers for Fundamental Matrix Estimation
According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator.
Robust Regression via Deep Negative Correlation Learning
Nonlinear regression has been extensively employed in many computer vision problems (e. g., crowd counting, age estimation, affective computing).
Scoot: A Perceptual Metric for Facial Sketches
In this paper, we design a perceptual metric, called Structure Co-Occurrence Texture (Scoot), which simultaneously considers the block-level spatial structure and co-occurrence texture statistics.
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
The use of RGB-D information for salient object detection has been extensively explored in recent years.
Ranked #4 on
RGB-D Salient Object Detection
on RGBD135
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.
Detecting Anemia from Retinal Fundus Images
Despite its high prevalence, anemia is often undetected due to the invasiveness and cost of screening and diagnostic tests.
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs).
Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality
Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information.
Similar Image Search for Histopathology: SMILY
SMILY may be a useful general-purpose tool in the pathologist's arsenal, to improve the efficiency of searching large archives of histopathology images, without the need to develop and implement specific tools for each application.
Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection
OOF is often only detected upon careful review, potentially causing rescanning and workflow delays.
Salient Object Detection via High-to-Low Hierarchical Context Aggregation
In this paper, we observe that the contexts of a natural image can be well expressed by a high-to-low self-learning of side-output convolutional features.
Deep Learning and Glaucoma Specialists: The Relative Importance of Optic Disc Features to Predict Glaucoma Referral in Fundus Photos
An algorithm trained on fundus images alone can detect referable GON with higher sensitivity than and comparable specificity to eye care providers.
Microscope 2.0: An Augmented Reality Microscope with Real-time Artificial Intelligence Integration
We demonstrate the utility of ARM in the detection of lymph node metastases in breast cancer and the identification of prostate cancer with a latency that supports real-time workflows.
Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer
For prostate cancer patients, the Gleason score is one of the most important prognostic factors, potentially determining treatment independent of the stage.
MatchBench: An Evaluation of Feature Matchers
This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly.
Crowd Counting With Deep Negative Correlation Learning
Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks.
Ranked #9 on
Crowd Counting
on WorldExpo’10
Learning Pixel-wise Labeling from the Internet without Human Interaction
Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation.
Semantic Edge Detection with Diverse Deep Supervision
Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition.
Personalized Recommender System for Children's Book Recommendation with A Realtime Interactive Robot
In this paper we study the personalized book recommender system in a child-robot interactive environment.
Image Matching: An Application-oriented Benchmark
To this end, we present a uniform benchmark with novel evaluation metrics and a large-scale dataset for evaluating the overall performance of image matching methods.
Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
Traditionally, medical discoveries are made by observing associations and then designing experiments to test these hypotheses.
Structure-measure: A New Way to Evaluate Foreground Maps
Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map.
Detecting Cancer Metastases on Gigapixel Pathology Images
At 8 false positives per image, we detect 92. 4% of the tumors, relative to 82. 7% by the previous best automated approach.
Ranked #2 on
Medical Object Detection
on Barrett’s Esophagus
Richer Convolutional Features for Edge Detection
Using VGG16 network, we achieve \sArt results on several available datasets.
Ranked #4 on
Edge Detection
on BIPED
Transferring Knowledge from Text to Predict Disease Onset
Specifically, we use word2vec models trained on a domain-specific corpus to estimate the relevance of each feature's text description to the prediction problem.
Sequential Optimization for Efficient High-Quality Object Proposal Generation
We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.
