thegregyang / LossUpAccUp
Loss and accuracy go opposite ways...right?
☆90Updated 4 years ago
Related projects: ⓘ
- Unsupervised Data Augmentation experiments in PyTorch☆59Updated 5 years ago
- Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)☆110Updated 3 years ago
- FlatNCE: A Novel Contrastive Representation Learning Objective☆83Updated 2 years ago
- [ICML 2020] code for the flooding regularizer proposed in "Do We Need Zero Training Loss After Achieving Zero Training Error?"☆91Updated last year
- PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018☆123Updated 4 years ago
- Implementation of Online Label Smoothing in PyTorch☆94Updated last year
- ☆76Updated last year
- Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"☆117Updated last year
- Improving generalization by controlling label-noise information in neural network weights.☆39Updated 3 years ago
- ICML 2019: Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels☆90Updated 3 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆82Updated 5 years ago
- [ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels☆132Updated 2 months ago
- Reproduce Results for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels" https://arxiv.org/abs/1908.06112☆181Updated 3 years ago
- Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"☆153Updated 4 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆82Updated last month
- Official Implementation of ICML 2019 Unsupervised label noise modeling and loss correction☆219Updated 4 years ago
- Implementation of OmniNet, Omnidirectional Representations from Transformers, in Pytorch☆53Updated 3 years ago
- ☆55Updated 3 years ago
- Code for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels"☆168Updated 3 years ago
- A supplementary code for Editable Neural Networks, an ICLR 2020 submission.☆46Updated 4 years ago
- Bootstrapping loss function implementation in pytorch☆36Updated 3 years ago
- MoPro: Webly Supervised Learning☆87Updated 3 years ago
- Full implementation of the paper "Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator".☆99Updated 4 years ago
- A collection of awesome things about mixed sample data augmentation☆130Updated 4 years ago
- CVPR'20: Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization☆124Updated 10 months ago
- When Does Label Smoothing Help?_pytorch_implementationimp☆124Updated 4 years ago
- Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)☆105Updated 2 years ago
- ☆129Updated last year
- Pytorch implementation of Virtual Adversarial Training☆132Updated 5 years ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆156Updated 3 years ago