When working with python libraries, especially for visualization, I usually get confused my number of options available for plotting. Example:
1. plt.plot() 2. ax = plt.subplot() ax.plot(x, y) 3. fig1, ((ax1, ax2), (ax3, ax4)) = plt.
Paper: Learning Transferable Visual Models From Natural Language Supervision
PDF: Learning Transferable Visual Models From Natural Language Supervision
Blog: CLIP: Connecting Text and Images
iNat2017 Data: https://github.com/visipedia/inat_comp/tree/master/2017 iNat2018 and iNat2019 Data: https://github.com/visipedia/inat_comp/blob/master/2018/README.md Data: https://github.com/visipedia/inat_comp Details: The dataset is similar to iNat2017 with small differences, which are mentioned in the website.
What is KL-Divergence KL Divergence is a measure of how one probabilty distributon is different from another. Some people also call it the distance between two distributions, however, strictly speaking it is not the distance.
Question: If a class has only two samples, can a computer make correct prediction? Note: Number of samples is too less for training.
Approach: Few Shot Learning
Few shot learning is a problem where we try to learn when the training data is very small.
Explores how can we use additional meta-data available to make better classification (in this case animal species). Explores how to make best use of additional meta data which comes with most images today.
Focuses on species of plants and animals captured in wide variety of situations, different camera types, varying image quality, feature large class imbalance and verified by citizen scientists.
Objective: Leverage free, noisy data from the web to train effective models of fine-grained recognition.
Interesting paper on using noisy data from the web. They sample images directly from Google search, using all returned images as images for a given category.