From 0f5d4ab5e47a8e671a567c66072d91e983d8b8a6 Mon Sep 17 00:00:00 2001 From: Yoshitomo Matsubara Date: Mon, 14 Aug 2023 08:27:09 -0700 Subject: [PATCH 1/2] Add descriptions --- docs/source/index.rst | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/docs/source/index.rst b/docs/source/index.rst index 3e08b89c..32c54cf0 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -9,9 +9,30 @@ SC2 Benchmark documentation SC2: Supervised Compression for Split Computing *********************************************** +This is the official documentation of ``sc2bench`` package and +our TMLR paper, :ref:`"SC2 Benchmark: Supervised Compression for Split Computing"`_. + .. image:: https://raw.githubusercontent.com/yoshitomo-matsubara/sc2-benchmark/main/imgs/input_vs_supervised_compression.png :alt: Supervised Compression for Split Computing +As an intermediate option between local computing and edge computing (full offloading), +**split computing** has been attracting considerable attention from the research communities. + +In split computing, we split a neural network model into two sequences so that +some elementary feature transformations are applied by the first sequence of the model on a weak mobile (local) device. +Then, intermediate, informative features are transmitted through a wireless communication channel to +a powerful edge server that processes the bulk part of the computation (the second sequence of the model). + +Input compression is an approach to save transmitted data, but it leads to transmitting information irrelevant to +the supervised task. +To achieve better supervised rate-distortion tradeoff, we define ***supervised compression*** as +learning compressed representations for supervised downstream tasks such as classification, detection, or segmentation. +Specifically for split computing, we term the problem setting **SC2** (*Supervised Compression for Split Computing*). + +Note that the training process can be done offline (i.e., on a single device without splitting), +and it is different from "split learning". + + Check out the :doc:`usage` section for further information. .. toctree:: From 4301aa93172d94bdc402004270ce555f117073a8 Mon Sep 17 00:00:00 2001 From: Yoshitomo Matsubara Date: Mon, 14 Aug 2023 08:36:34 -0700 Subject: [PATCH 2/2] Add links to PyPI package --- docs/source/index.rst | 5 +++-- docs/source/usage.rst | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/source/index.rst b/docs/source/index.rst index 32c54cf0..e398b770 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -9,12 +9,13 @@ SC2 Benchmark documentation SC2: Supervised Compression for Split Computing *********************************************** -This is the official documentation of ``sc2bench`` package and -our TMLR paper, :ref:`"SC2 Benchmark: Supervised Compression for Split Computing"`_. .. image:: https://raw.githubusercontent.com/yoshitomo-matsubara/sc2-benchmark/main/imgs/input_vs_supervised_compression.png :alt: Supervised Compression for Split Computing +This is the official documentation of `sc2bench `_ package and +our TMLR paper, `"SC2 Benchmark: Supervised Compression for Split Computing" `_. + As an intermediate option between local computing and edge computing (full offloading), **split computing** has been attracting considerable attention from the research communities. diff --git a/docs/source/usage.rst b/docs/source/usage.rst index ff64bade..1025a145 100644 --- a/docs/source/usage.rst +++ b/docs/source/usage.rst @@ -9,7 +9,7 @@ Usage Installation ------------ -To use `sc2bench`, first install it using pip: +To use `sc2bench `_, first install it using pip: .. code-block:: console