Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]

Code for MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks

[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels

AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

AAAI 2021: Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels

MIL-RBERT: A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction (BioNLP @ ACL 2020)

Code from paper High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction

Dynamic Mixing For Speech Processing (mix-on-the-fly)

A collection of algorithms for detecting and handling label noise

Enhanced awesome-align for low-resource languages and noise simulation: https://arxiv.org/abs/2301.09685

Self-Supervised Learning for Outlier Detection.

🍷 Code for Noisy Pairing and Partial Supervision for Stylized Opinion Summarization (Iso et al; INLG 2024)

Implementations of various NMF algorithms on the ORL and cropped YaleB datasets.

Least squares and recursive least squares implementation. 2D line fit to noisy data.

Methods for numerical differentiation of noisy data in python

This implementation is based on the multi-task label cleaning network proposed by Inoue et. al. in the paper "Multi-Label Fashion Image Classification with Minimal Human Supervision"