Home /

Research

Showing 31 - 36 / 897

The large learning rate phase of deep learning


Authors:  Anonymous....
Published date-01/01/2021

Abstract: The choice of initial learning rate can have a profound effect on the performance of deep networks. We present empirical evidence that networks exhibit sharply distinct behaviors at small and …

Contrast to Divide: self-supervised pre-training for learning with noisy labels


Authors:  Anonymous....
Published date-01/01/2021
Tasks:  ImageClassification, Learningwithnoisylabels

Abstract: Advances in semi-supervised methods for image classification significantly boosted performance in the learning with noisy labels (LNL) task. Specifically, by discarding the erroneous labels (and keeping the samples), the LNL …

Ruminating Word Representations with Random Noise Masking


Authors:  Anonymous....
Published date-01/01/2021
Tasks:  TextClassification, WordEmbeddings

Abstract: We introduce a training method for better word representation and performance, which we call \textbf{GraVeR} (\textbf{Gra}dual \textbf{Ve}ctor \textbf{R}umination). The method is to gradually and iteratively add random noises and bias …

Hierarchical Meta Reinforcement Learning for Multi-Task Environments


Authors:  Anonymous....
Published date-01/01/2021
Tasks:  HierarchicalReinforcementLearning, MetaReinforcementLearning

Abstract: Deep reinforcement learning algorithms aim to achieve human-level intelligence by solving practical decisions-making problems, which are often composed of multiple sub-tasks. Complex and subtle relationships between sub-tasks make traditional methods …

How Robust are Randomized Smoothing based Defenses to Data Poisoning?


Authors:  AkshayMehra, BhavyaKailkhura, Pin-YuChen....
Published date-12/02/2020
Tasks:  bileveloptimization, DataAugmentation, DataPoisoning

Abstract: The prediction of certifiably robust classifiers remains constant around a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously …

PlueckerNet: Learn to Register 3D Line Reconstructions


Authors:  LiuLiu, HongdongLi, HaodongYao....
Published date-12/02/2020

Abstract: Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network …

Filter by

Categories

Tags