Comments (2)
thoughts?
Another benefit is that Task2Vec method does not rely on activations from an arbitrarily selected layer in a network.
Lastly, note that activations may be unreliable for embedding dataset/tasks because large distances between datasets/tasks may be due to well-separated decision boundaries instead of intrinsic semantic properties of the dataset/task.
In contrast, the diversity coefficient is well-justified, extensively tested in our work and previous work, e.g. the diversity coefficient correlates with ground truth diversities, cluster according to semantics, taxonomy etc. (see section \ref{appendix:ground_truth_div} and \cite{task2vec, curse_low_div}).
In short, FIM based representations are motivated by information theory (e.g. FIMs are metrics in distributions) and have been extensively tested by independent sources \citep{curse_low_div, task2vec, nlp_task2vec}.
% main argument against activations is that the distance can be very large very randomly due to decision boundaries rather than intrinsic data properties e.g. models might try to maximize distance (SVMs)
from aws-cv-task2vec.
from aws-cv-task2vec.
Related Issues (20)
- Missing Files
- Missing txt files
- Why is task2vec agnostic to the model? HOT 6
- Reproducing semantic clustering and taxonomical correlation HOT 1
- what would a task2vec (cosine) distance of -1 mean? HOT 1
- How to add new dataset,
- task2vec complexity using normalized/standardized values
- probe network need to re-train head for each task?
- How to handle single data points? how does task2vec work in this setting?
- Strengths and weaknesses of task2vec?
- readme missing citation
- What is the exact relationship of Task2Vec (FIM) and Kolmogorov Complexity? HOT 1
- Are you sure .train() puts batch norm in eval mode? I'd assume that means train... HOT 2
- citation quote on the readme would help cite repo/project
- cannot compute distance matrix for only mnist HOT 1
- speeding up FIM computation
- Are task2vec embeddings valid when the network used doesn't perfectly fit the data? HOT 1
- Replication
- Can the true entropy of the distribution of a task be computed using task2vec?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from aws-cv-task2vec.