Deep Learning for Computer Vision: Image Classification (UPC 2016)
4 likes4,315 views
The document discusses image classification, highlighting the importance of train/test splits, metrics, and models in building predictive systems. It emphasizes a structured approach to data preparation and performance assessment, as well as outlines various metrics like accuracy, precision, and recall. Additionally, it introduces the role of linear models and neurons in neural network architecture for classification tasks.
![Day 1 Lecture 2
Classification
[course site]
Eva Mohedano](https://image.slidesharecdn.com/dlcvd1l2classification-160715093559/85/Deep-Learning-for-Computer-Vision-Image-Classification-UPC-2016-1-320.jpg)
![4
Image Classification
Set of predefined categories [eg: table, apple, dog, giraffe]
Binary classification [1, 0]
DOG](https://image.slidesharecdn.com/dlcvd1l2classification-160715093559/85/Deep-Learning-for-Computer-Vision-Image-Classification-UPC-2016-4-320.jpg)
Deep Learning for Computer Vision: Image Classification (UPC 2016)
- 1. Day 1 Lecture 2 Classification [course site] Eva Mohedano
- 4. 4 Image Classification Set of predefined categories [eg: table, apple, dog, giraffe] Binary classification [1, 0] DOG
- 6. 6 Dog Image Classification pipeline Slide credit: Jose M Àlvarez
- 7. 7Slide credit: Jose M Àlvarez Dog Learned Representation Image Classification pipeline
- 8. 8 Dog Learned Representation Part I: End-to-end learning (E2E) Image Classification pipeline Slide credit: Jose M Àlvarez
- 9. 9 Image Classification: Example Datasets training set of 60,000 examples test set of 10,000 examples
- 10. 10 Image Classification: Example Datasets
- 12. 2.1 3.2 4.8 0.1 0.0 2.6 3.1 1.4 2.5 0.2 1.0 2.0 1.0 2.3 3.2 9.3 6.4 0.3 2.0 5.0 3.2 1.0 6.9 9.1 9.0 3.5 5.4 5.5 3.2 1.0 N training examples (rows) D features (columns) 0 1 1 0 0 N Training set
- 13. Dataset Shuffled data shuffle Training data (70%) Test data (30%) split Learning algorithm fit(X, y) Model Prediction algorithm predict(X) Predictions Compute error/accuracy score(X, y) Out-of-sample error estimate NO! Train/Test Splits
- 14. Split your dataset into train and test at the very start ● Usually good practice to shuffle data (exception: time series) Do not look at test data (data snooping)! ● Lock it away at the start to prevent contamination NB: Never ever train on the test data! ● You have no way to estimate error if you do ● Your model could easily overfit the test data and have poor generalization, you have no way of knowing without test data ● Model may fail in production Data hygiene
- 16. Confusion matrices provide a by-class comparison between the results of the automatic classifications with ground truth annotations. Metrics
- 17. Metrics Correct classifications appear in the diagonal, while the rest of cells correspond to errors. Prediction Class 1 Class 2 Class 3 Ground Truth Class 1 x(1,1) x(1,2) x(1,3) Class 2 x(2,1) x(2,2) x(2,3) Class 3 x(3,1) x(3,2) x(3,3)
- 18. Special case: Binary classifiers in terms of “Positive” vs “Negative”. Prediction Positives negative Ground Truth Positives True positive (TP) False negative (FN) negative False positives (FP) True negative (TN) Metrics
- 19. The “accuracy” measures the proportion of correct classifications, not distinguishing between classes. Binary Prediction Class 1 Class 2 Class 3 Ground Truth Class 1 x(1,1) x(1,2) x(1,3) Class 2 x(2,1) x(2,2) x(2,3) Class 3 x(3,1) x(3,2) x(3,3) Prediction Positives negative Ground Truth Positives True positive (TP) False negative (FN) Negative False positives (FP) True negative (TN) Metrics
- 20. Given a reference class, its Precision (P) and Recall (R) are complementary measures of relevance. Prediction Positives Negatives Ground Truth Positives True positive (TP) False negative (FN) Negatives False positives (FP) "Precisionrecall" by Walber - Own work. Licensed under Creative Commons Attribution-Share Alike 4.0 via Wikimedia Commons - http://commons.wikimedia.org/wiki/File:Precisionrecall. svg#mediaviewer/File:Precisionrecall.svg Example: Relevant class is “Positive” in a binary classifier. Metrics
- 21. Binary classification results often depend from a parameter (eg. decision threshold) whose value directly impacts precision and recall. For this reason, in many cases a Receiver Operating Curve (ROC curve) is provided as a result. TruePositiveRate Metrics
- 23. 23 Dog Image Classification pipeline Slide credit: Jose M Àlvarez
- 24. Mapping function to predict a score for the class label Linear Models f(x, w) = (wT x + b) CS231n: Convolutional Neural Networks for Visual Recognition
- 25. Sigmoid f(x, w) = g(wT x + b) Activation function: Turn score into probabilities Logistic Regression
- 26. Neuron
- 27. Summary Image classification aims to build a model to automatically predict the content of an image. When presented as supervised problem, data should be structured in Train/Test splits to learn the model. Important to have a way to asses the performance of the models Easiest models classification are linear models. Linear models with a non-linearity on top represent the the “neuron”, the basic element of Neural Networks.