CHIA: Concept Hierarchies for Incremental and Active Learning
CHIA implements methods centered around hierarchical classification in a lifelong learning environment. It forms the basis for some of the experiments and tools developed at Computer Vision Group Jena. Development is continued at the DLR Institute of Data Science
Methods
CHIA implements:
- One-Hot Softmax Classifier as a baseline.
- Probabilistic Hierarchical Classifier Brust, C. A., & Denzler, J. (2019). Integrating domain knowledge: using hierarchies to improve deep classifiers. In Asian Conference on Pattern Recognition (ACPR)
- CHILLAX Brust, C. A., Barz, B., & Denzler, J. (2021). Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge. In International Conference on Pattern Recognition (ICPR).
- Self-Supervised CHILLAX Brust, C. A., Barz, B., & Denzler, J. (2022). Self-Supervised Learning from Semantically Imprecise Data. In Computer Vision Theory and Applications (VISAPP)
- Semantic Label Sharing Fergus, R., Bernal, H., Weiss, Y., & Torralba, A. (2010). Semantic label sharing for learning with many categories. In European Conference on Computer Vision (ECCV).
Datasets
CHIA has integrated support including hierarchies for a number of popular datasets. See here for a complete list.
Installation and Getting Started
CHIA is available on PyPI. To install, simply run:
pip install chia
or clone this repository, and run:
pip install -e .
To run the example experiment which makes sure that everything works, use the following command:
python examples/experiment.py examples/configuration.json
After a few minutes, the last lines of output should look like this:
[SHUTDOWN] [Experiment] Successful: True
Documentation
The following articles explain more about CHIA:
- Architecture explains the overall construction. It also includes reference descriptions of most classes.
- Configuration describes how experiments and CHIA itself are configured.
- Using your own dataset explains our JSON format for adding your own data.
Citation
If you use CHIA for your research, kindly cite:
Brust, C. A., & Denzler, J. (2019). Integrating domain knowledge: using hierarchies to improve deep classifiers. In Asian Conference on Pattern Recognition. Springer, Cham.
You can refer to the following BibTeX:
@inproceedings{Brust2019IDK,
author = {Clemens-Alexander Brust and Joachim Denzler},
booktitle = {Asian Conference on Pattern Recognition (ACPR)},
title = {Integrating Domain Knowledge: Using Hierarchies to Improve Deep Classifiers},
year = {2019},
doi = {10.1007/978-3-030-41404-7_1}
}
1 maintainer
Metadata
1 maintainer
Release files for chia 2.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| chia-2.5.0.tar.gz | 74.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| chia-2.5.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 178.0 kB
Release files / chia-2.5.0.tar.gz
| Download URL | chia-2.5.0.tar.gz |
|---|---|
| Size | 74.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ee0ee8dc1d3ddac1220032a314e247e8819722ad0ea34e615060cb0109c4a3fc
|
|
BLAKE2b-256 checksum How to use checksums |
6b3c5d34b6146b2a6e437795093e1c5b16b3fa86cf661ae4fba5d9da5ad6c1f3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.1
|
Release files / chia-2.5.0-py3-none-any.whl
| Download URL | chia-2.5.0-py3-none-any.whl |
|---|---|
| Size | 103.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
656f5deae9730d88728e160d135f9fca7f9a852fbfafb2c3d16bb3f02ac94a83
|
|
BLAKE2b-256 checksum How to use checksums |
7f9e86e8b8e0b6d02f4ee4da1a168d289ce0f268de4021ccfc1812a378071131
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.1
|
Security for chia 2.5.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
