In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.
Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets.
In this paper, we present a simple yet effective method (ABSGD) for addressing the data imbalance issue in deep learning.
We also explored the use of Graph Neural Networks and introduced a novel ensemble GNN architecture which outperformed the GNN solution from last year.
Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery.
In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.
The Empirical Revenue Maximization (ERM) is one of the most important price learning algorithms in auction design: as the literature shows it can learn approximately optimal reserve prices for revenue-maximizing auctioneers in both repeated auctions and uniform-price auctions.
With the recent progress of deep learning, advanced industrial object detectors are built for smart industrial applications.
Ranked #17 on Weakly Supervised Object Detection on PASCAL VOC 2007
To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples.
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods.
Ranked #1 on Hand Pose Estimation on MSRA Hands
To tackle these problems, we design a post-training procedure, which contains the target domain masked language model task and a novel domain-distinguish pre-training task.
The proposed online stochastic method resembles the practical stochastic Nesterovs method in several perspectives that are widely used for learning deep neural networks.
Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.
It has been demonstrated that multiple senses of a word actually reside in linear superposition within the word embedding so that specific senses can be extracted from the original word embedding.
Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage.
In this paper, we propose new stochastic optimization algorithms and study their first-order convergence theories for solving a broad family of DC functions.
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.
As most weakly supervised object detection methods are based on pre-generated proposals, they often show two false detections: (i) group multiple object instances with one bounding box, and (ii) focus on only parts rather than the whole objects.
Ranked #20 on Weakly Supervised Object Detection on PASCAL VOC 2007