The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021

Last update: Jan 01, 2023

Related tags

Deep Learning DER-ClassIL.pytorch

Overview

DER.ClassIL.Pytorch

This repo is the official implementation of DER: Dynamically Expandable Representation for Class Incremental Learning (CVPR 2021)

Dataset

ImageNet100 Refer to ImageNet100_Split

Training

Change to corresponding directory and run the following commands

sh scripts/run.sh

Inference

Inference command:

sh scripts/inference.sh

Tips

create a new exp folder

rsync -rv --exclude=tensorboard --exclude=logs --exclude=ckpts --exclude=__pycache__ --exclude=results --exclude=inbox ./codes/base/ ./exps/der_womask/10steps/trial0

Acknowledgement

Thanks for the great code base from https://github.com/arthurdouillard/incremental_learning.pytorch.

Citation

If you are using the DER in your research or with to refer to the baseline results published in this repo, please use the following BibTex entry.

@article{yan2021dynamically,
  title={DER: Dynamically Expandable Representation for Class Incremental Learning},
  author={Yan, Shipeng and Xie, Jiangwei and He, Xuming},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021}
}

The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021

Related tags

Overview

DER.ClassIL.Pytorch

Dataset

Training

Inference

Tips

Acknowledgement

Citation

Owner

rhyssiyan

PyTorch implementation of "A Two-Stage End-to-End System for Speech-in-Noise Hearing Aid Processing"

Source code of article "Towards Toxic and Narcotic Medication Detection with Rotated Object Detector"

Real-time Object Detection for Streaming Perception, CVPR 2022

Disease Informed Neural Networks (DINNs) — neural networks capable of learning how diseases spread, forecasting their progression, and finding their unique parameters (e.g. death rate).

realsense d400 -> jpg + csv

DeepVoxels is an object-specific, persistent 3D feature embedding.

Make Watson Assistant send messages to your Discord Server

Split your patch similarly to `git add -p` but supporting multiple buckets

Python library containing BART query generation and BERT-based Siamese models for neural retrieval.

Self-Supervised Learning of Event-based Optical Flow with Spiking Neural Networks

This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"

Self-Supervised Image Denoising via Iterative Data Refinement

A transformer which can randomly augment VOC format dataset (both image and bbox) online.

simple_pytorch_example project is a toy example of a python script that instantiates and trains a PyTorch neural network on the FashionMNIST dataset

Histocartography is a framework bringing together AI and Digital Pathology

Trading environnement for RL agents, backtesting and training.

QR2Pass-project - A proof of concept for an alternative (passwordless) authentication system to a web server

Implicit Model Specialization through DAG-based Decentralized Federated Learning

MLJetReconstruction - using machine learning to reconstruct jets for CMS

OpenMMLab Pose Estimation Toolbox and Benchmark.