Search Results for author:
Found 21 papers, 7 papers with code
MetaWeighting: Learning to Weight Tasks in Multi-Task Learning
Task weighting, which assigns weights on the including tasks during training, significantly matters the performance of Multi-task Learning (MTL); thus, recently, there has been an explosive interest in it.
Adaptive Adversarial Multi-task Representation Learning
Adversarial Multi-task Representation Learning (AMTRL) methods are able to boost the performance of Multi-task Representation Learning (MTRL) models.
Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data
In this paper, we study the confidence set prediction problem in the OOD generalization setting.
LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations.
Deep Partial Multi-Label Learning with Graph Disambiguation
In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels.
Generalization Bounds for Adversarial Contrastive Learning
Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model.
An Application of Deep Learning for Sweet Cherry Phenotyping using YOLO Object Detection
Tree fruit breeding is a long-term activity involving repeated measurements of various fruit quality traits on a large number of samples.
Better Diffusion Models Further Improve Adversarial Training
Under the $\ell_\infty$-norm threat model with $\epsilon=8/255$, our models achieve $70. 69\%$ and $42. 67\%$ robust accuracy on CIFAR-10 and CIFAR-100, respectively, i. e. improving upon previous state-of-the-art models by $+4. 58\%$ and $+8. 03\%$.
WAT: Improve the Worst-class Robustness in Adversarial Training
Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies.
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect.
EPPAC: Entity Pre-typing Relation Classification with Prompt AnswerCentralizing
To address these issues, a novel paradigm, Entity Pre-typing Relation Classification with Prompt Answer Centralizing(EPPAC) is proposed in this paper.
PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios.
Optical Character Recognition
Optical Character Recognition (OCR)
BanditMTL: Bandit-based Multi-task Learning for Text Classification
Task variance regularization, which can be used to improve the generalization of Multi-task Learning (MTL) models, remains unexplored in multi-task text classification.
The Emerging Trends of Multi-Label Learning
Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data.
Leveraged Matrix Completion with Noise
In this paper, we employ the leverage scores to characterize the importance of each element and significantly relax assumptions to: (1) not any other structure assumptions are imposed on the underlying low-rank matrix; (2) elements being observed are appropriately dependent on their importance via the leverage score.
PP-OCR: A Practical Ultra Lightweight OCR System
Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17. 9M images are used).
Tchebycheff Procedure for Multi-task Text Classification
Multi-task Learning methods have achieved great progress in text classification.
Opinion Maximization in Social Trust Networks
However, the practical significance of the existing studies on this subject is limited for two reasons.
Social and Information Networks Computer Science and Game Theory J.4
Copula Multi-label Learning
This inspires us to develop a novel copula multi-label learning paradigm for modeling label and feature dependencies.
Sparse Embedded k-Means Clustering
For example, compared to the advanced singular value decomposition based feature extraction approach, [1] reduce the running time by a factor of $\min \{n, d\}\epsilon^2 log(d)/k$ for data matrix $X \in \mathbb{R}^{n\times d} $ with $n$ data points and $d$ features, while losing only a factor of one in approximation accuracy.
On the Optimality of Classifier Chain for Multi-label Classification
Based on our results, we propose a dynamic programming based classifier chain (CC-DP) algorithm to search the globally optimal label order for CC and a greedy classifier chain (CC-Greedy) algorithm to find a locally optimal CC.
