paper-with-me

홈 › Papers

A method of limiting performance loss of CNNs in noisy environments

2017-02-03 · James R. Geraci, Parichay Kapoor

Convolutional Neural Network (CNN) recognition rates drop in the presence of noise. We demonstrate a novel method of counteracting this drop in recognition rate by adjusting the biases of the neurons in the convolutional layers according to the noise conditions encountered at runtime. We compare our technique to training one network for all possible noise levels, dehazing via preprocessing a signal with a denoising autoencoder, and training a network specifically for each noise level. Our system compares favorably in terms of robustness, computational complexity and recognition rate.

📄 PDF Abstract BibTeX arXiv:1702.00932

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Similar Papers 제목 키워드 기반

Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels

2024-10-05 · Maria Marrium, Arif Mahmood, Mohammed Bennamoun

Automatic annotation of large-scale datasets can introduce noisy training data labels, which adversely affect the learning process of deep neural networks (DNNs). Consequently, Noisy Labels Learning (NLL) has become a cr…

Benchmarking

Self-paced Resistance Learning against Overfitting on Noisy Labels

2021-05-07 · Xiaoshuang Shi, Zhenhua Guo, Kang Li, Yun Liang 외

Noisy labels composed of correct and corrupted ones are pervasive in practice. They might significantly deteriorate the performance of convolutional neural networks (CNNs), because CNNs are easily overfitted on corrupted…

Memorization

Joint Negative and Positive Learning for Noisy Labels

2021-04-14 · CVPR 2021 1 · Youngdong Kim, Juseung Yun, Hyounguk Shon, Junmo Kim

Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs…

Singular-limit analysis of gradient descent with noise injection

2024-04-18 · Anna Shalova, André Schlichting, Mark Peletier

We study the limiting dynamics of a large class of noisy gradient descent systems in the overparameterized regime. In this regime the set of global minimizers of the loss is large, and when initialized in a neighbourhood…

Dense-TSNet: Dense Connected Two-Stage Structure for Ultra-Lightweight Speech Enhancement

2024-09-18 · Zizhen Lin, Yuanle Li, Junyu Wang, Ruili Li

Speech enhancement aims to improve speech quality and intelligibility in noisy environments. Recent advancements have concentrated on deep neural networks, particularly employing the Two-Stage (TS) architecture to enhanc…

MambaSpeech Enhancement