Search Results for author:
Found 40 papers, 13 papers with code
AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation
Online knowledge distillation has attracted increasing interest recently, which jointly learns teacher and student models or an ensemble of student models simultaneously and collaboratively.
DeepBlueAI at WANLP-EACL2021 task 2: A Deep Ensemble-based Method for Sarcasm and Sentiment Detection in Arabic
Sarcasm is one of the main challenges for sentiment analysis systems due to using implicit indirect phrasing for expressing opinions, especially in Arabic.
DeepBlueAI at TextGraphs 2021 Shared Task: Treating Multi-Hop Inference Explanation Regeneration as A Ranking Problem
This paper describes the winning system for TextGraphs 2021 shared task: Multi-hop inference explanation regeneration.
Tackling Small Sample Survival Analysis via Transfer Learning: A Study of Colorectal Cancer Prognosis
For non-parametric models such as Random Survival Forest, we propose a new transfer survival forest (TSF) model that transfers tree structures from source tasks and fine-tunes them with target data.
Continual Learning for Smart City: A Survey
We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends.
A Survey of Route Recommendations: Methods, Applications, and Opportunities
Our survey offers a comprehensive review of route recommendation work based on urban computing.
Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations.
Modeling Continuous Motion for 3D Point Cloud Object Tracking
The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics.
DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention
3D object detection with surround-view images is an essential task for autonomous driving.
Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors.
Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer
In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames given an object template.
TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection
3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics.
Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation
Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes.
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection.
Accelerating DETR Convergence via Semantic-Aligned Matching
First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
PTTR: Relational 3D Point Cloud Object Tracking with Transformer
In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud.
GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data
Specifically, we design GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training.
MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples.
AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Data
Temporal relational data, perhaps the most commonly used data type in industrial machine learning applications, needs labor-intensive feature engineering and data analyzing for giving precise model predictions.
DeepBlueAI at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Stacking Diverse Language Model-Based Methods
This paper describes the winning system for SemEval-2021 Task 7: Detecting and Rating Humor and Offense.
DeepBlueAI at SemEval-2021 Task 1: Lexical Complexity Prediction with A Deep Ensemble Approach
Lexical complexity plays an important role in reading comprehension.
Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency
In addition, existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
Compared with single-source unsupervised domain adaptation (SUDA), domain shift in MUDA exists not only between the source and target domains but also among multiple source domains.
Classification
Multi-Source Unsupervised Domain Adaptation
+2
DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
DA-DETR introduces a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains.
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks.
Ranked #9 on
Few-Shot Object Detection
on MS-COCO (30-shot)
BERT-based Acronym Disambiguation with Multiple Training Strategies
Acronym disambiguation (AD) task aims to find the correct expansions of an ambiguous ancronym in a given sentence.
Counting and Locating High-Density Objects Using Convolutional Neural Network
For the tree dataset, our method returned a mean absolute error (MAE) of 2. 05, a root-mean-squared error (RMSE) of 2. 87 and a coefficient of determination (R$^2$) of 0. 986.
Semantic Segmentation with Labeling Uncertainty and Class Imbalance
Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
A Technical Report for VIPriors Image Classification Challenge
This paper is a brief report to our submission to the VIPriors Image Classification Challenge.
VIPriors Object Detection Challenge
This paper is a brief report to our submission to the VIPriors Object Detection Challenge.
Challenge report:VIPriors Action Recognition Challenge
This paper is a brief report to our submission to the VIPriors Action Recognition Challenge.
Efficient Architecture Search for Continual Learning
To reach these goals, we propose a novel approach named as Continual Learning with Efficient Architecture Search, or CLEAS in short.
Challenge report: Recognizing Families In the Wild Data Challenge
In this paper, we studied previous methods and proposed our method.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
PointNLM: Point Nonlocal-Means for vegetation segmentation based on middle echo point clouds
Second, to accurately extract trees from all point clouds, we propose a 3D deep learning network, PointNLM, to semantically segment tree crowns.
Learning Fast Matching Models from Weak Annotations
The proposed training framework targets on mitigating both issues, by treating the stronger but undeployable models as annotators, and learning a deployable model from both human provided relevance labels and weakly annotated search log data.
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision.
