[SOLVED] Machine-Learning- HW3: Image Classification

Description

Objective

1. Solve image classification with convolutional neural networks.
2. Improve the performance with data augmentations.
3. Understand how to utilize unlabeled data and how it benefits.

• The images are collected from the food-11 dataset classified into 11 classes.
• The dataset here is slightly modified:
• Training set: 280 * 11 labeled images + 6786 unlabeled images
• Validation set: 60 * 11 labeled images
• Testing set: 3347 images
• DO NOT utilize the original dataset or labels.

○     This is cheating.

Kaggle link: here

Requirements

• This homework is in three levels:
  • Easy

○    Medium

○    Hard

• You can easily finish the easy level by running the example code.
• For the rest, we recommend you start with the same code.
  • We already prepared some TODO blocks for you.
• DO NOT pre-train your model on other datasets.
• If you use some well-known model architecture (e.g., ResNet), make sure NOT to load pre-trained weights as initialization.

Requirements – Easy

• Build a convolutional neural network using labeled images with provided codes.
• Public simple baseline: 44.862 (accuracy, %)

Requirements – Medium

• Improve the performance using labeled images with different model architectures or data augmentations.
• Public medium baseline: 52.807 (accuracy, %)
• You can achieve the baseline by adding a few lines to the example code.

Requirements – Hard

• Improve the performance with additional unlabeled images.
• Public strong baseline: 82.138 (accuracy, %)
• Do it on your own (by finishing TODO blocks in the example code).
• Using unlabeled testing data here is allowed.
• Hint: semi-supervised learning, self-supervised learning

Semi-supervised Learning

• There are many ways to do semi-supervised learning.
• g., generate pseudo-labels for unlabeled data and train with them.

Pseudo-labels

Useful Resources

• Semi-supervised learning
  • https://speech.ee.ntu.edu.tw/~tlkagk/courses/ML_2016/Lecture/semi%20(v3).pdf

○           https://www.youtube.com/watch?v=fX_guE7JNnY&ab_channel=Hung-yiLee

○     MixMatch: https://arxiv.org/abs/1905.02249 ○       Noisy student: https://arxiv.org/abs/1911.04252

• PyTorch
  • https://pytorch.org/
• Torchvision
  • http://pytorch.org/vision/stable/index.html