mldl Goto Github PK
Type: Organization
Type: Organization
100 Days of ML Coding
PyTorch implementation for Partially View-aligned Representation Learning with Noise-robust Contrastive Loss (CVPR 2021)
3D Graph Neural Networks for RGBD Semantic Segmentation
Official Implementation of PVD:One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
Code Release for CVPR 2020, "ACNe: Attentive Context Normalizationfor Robust Permutation-Equivariant Learning"
Code for ICML2020 paper [“Normalized Loss Functions for Deep Learning with Noisy Labels"] https://arxiv.org/abs/2006.13554
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Official Implementation of NeurIPS 2023 paper "Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation"
Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"
Official code for ICLR 2024 paper Do Generated Data Always Help Contrastive Learning?
Slowing Down the Weight Norm Increase in Momentum-based Optimizers
exponential adaptive pooling for PyTorch
To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data. In this work, a novel methodology is proposed to adaptively customize activation functions only by adding very few parameters to the traditional activation functions such as Sigmoid, Tanh, and ReLU. To verify the effectiveness of the proposed methodology, some theoretical and experimental analysis on accelerating the convergence and improving the performance is presented, and a series of experiments are conducted based on various network models (such as AlexNet, VGGNet, GoogLeNet, ResNet and DenseNet), and various datasets (such as CIFAR10, CIFAR100, miniImageNet, PASCAL VOC and COCO) . To further verify the validity and suitability in various optimization strategies and usage scenarios, some comparison experiments are also implemented among different optimization strategies (such as SGD, Momentum, AdaGrad, AdaDelta and ADAM) and different recognition tasks like classification and detection. The results show that the proposed methodology is very simple but with significant performance in convergence speed, precision and generalization, and it can surpass other popular methods like ReLU and adaptive functions like Swish in almost all experiments in terms of overall performance.
The adaptively parametric ReLU is an activation function that performs non-identically for input samples.
Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
[CVPR 2023] Learning Attention as Disentangler for Compositional Zero-shot Learning
Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)
[CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
Code and hyperparameters for the paper "Generative Adversarial Networks"
Implementation for the paper "Adversarial Continual Learning" in PyTorch.
[NeurIPS 2020] “Adversarial Contrastive Learning: Harvesting More Robustness from Unsupervised Pre-Training”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
The classical papers and codes about generative adversarial nets
[ICML2020] "AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks" by Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan Lin, Zhangyang Wang
Large-batch Optimization for Dense Visual Predictions (NeurIPS 2022)
:alarm_clock: AI conference deadline countdowns
Roadmap to becoming an Artificial Intelligence Expert in 2021
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.