YOLO: What is better? multiple networks per label or multiple labels in single network? The 2019 Stack Overflow Developer Survey Results Are InAny differences in regularisation in MLP between batch and individual updates?In Neural Networks and deep neural networks what does label-dropout meanBatching in Recurrent Neural Networks (RNNs) when there is only a single instance per time step?What is the way to modify a neural network classifier to deal with sample points from outside of the label set?
Why isn't airport relocation done gradually?
What do hard-Brexiteers want with respect to the Irish border?
Is there a name of the flying bionic bird?
Idiomatic way to prevent slicing?
Why do UK politicians seemingly ignore opinion polls on Brexit?
How to create dashed lines/arrows in Illustrator
Confusion about non-derivable continuous functions
Monty Hall variation
Can I write a for loop that iterates over both collections and arrays?
In microwave frequencies, do you use a circulator when you need a (near) perfect diode?
How was Skylab's orbit inclination chosen?
Is "plugging out" electronic devices an American expression?
Which Sci-Fi work first showed weapon of galactic-scale mass destruction?
Inflated grade on resume at previous job, might former employer tell new employer?
Patience, young "Padovan"
What function has this graph?
Spanish for "widget"
How to reverse every other sublist of a list?
Does duplicating a spell with wish count as casting that spell?
Time travel alters history but people keep saying nothing's changed
Can't find the latex code for the ⍎ (down tack jot) symbol
Landlord wants to switch my lease to a "Land contract" to "get back at the city"
How long do I have to send payment?
"What time...?" or "At what time...?" - what is more grammatically correct?
YOLO: What is better? multiple networks per label or multiple labels in single network?
The 2019 Stack Overflow Developer Survey Results Are InAny differences in regularisation in MLP between batch and individual updates?In Neural Networks and deep neural networks what does label-dropout meanBatching in Recurrent Neural Networks (RNNs) when there is only a single instance per time step?What is the way to modify a neural network classifier to deal with sample points from outside of the label set?
$begingroup$
I would like to use a YOLO network, retrain it to recognize say, 20 labels.
Would adding labels to a single network in training reduce its accurary?
Would it be better to train multiple models on 5,10 and 5 labels respectively.
e.g.
Model A : recognizes 5 labels (ferrari,honda,ford,toyota,tesla)
Model B : regonzies 10 labels (store front / stopsign, speed sign, super charger station , etccc. )
Model C : recongizes 5 labels (pedestrian, dog, marathon runner, bicycler, scooter rider)
OR
Model D: Recognizes 20 labels (all labels above put together)
Would Model D be as accurate as Model A,B,C put together?
neural-network image-recognition yolo
New contributor
$endgroup$
add a comment |
$begingroup$
I would like to use a YOLO network, retrain it to recognize say, 20 labels.
Would adding labels to a single network in training reduce its accurary?
Would it be better to train multiple models on 5,10 and 5 labels respectively.
e.g.
Model A : recognizes 5 labels (ferrari,honda,ford,toyota,tesla)
Model B : regonzies 10 labels (store front / stopsign, speed sign, super charger station , etccc. )
Model C : recongizes 5 labels (pedestrian, dog, marathon runner, bicycler, scooter rider)
OR
Model D: Recognizes 20 labels (all labels above put together)
Would Model D be as accurate as Model A,B,C put together?
neural-network image-recognition yolo
New contributor
$endgroup$
add a comment |
$begingroup$
I would like to use a YOLO network, retrain it to recognize say, 20 labels.
Would adding labels to a single network in training reduce its accurary?
Would it be better to train multiple models on 5,10 and 5 labels respectively.
e.g.
Model A : recognizes 5 labels (ferrari,honda,ford,toyota,tesla)
Model B : regonzies 10 labels (store front / stopsign, speed sign, super charger station , etccc. )
Model C : recongizes 5 labels (pedestrian, dog, marathon runner, bicycler, scooter rider)
OR
Model D: Recognizes 20 labels (all labels above put together)
Would Model D be as accurate as Model A,B,C put together?
neural-network image-recognition yolo
New contributor
$endgroup$
I would like to use a YOLO network, retrain it to recognize say, 20 labels.
Would adding labels to a single network in training reduce its accurary?
Would it be better to train multiple models on 5,10 and 5 labels respectively.
e.g.
Model A : recognizes 5 labels (ferrari,honda,ford,toyota,tesla)
Model B : regonzies 10 labels (store front / stopsign, speed sign, super charger station , etccc. )
Model C : recongizes 5 labels (pedestrian, dog, marathon runner, bicycler, scooter rider)
OR
Model D: Recognizes 20 labels (all labels above put together)
Would Model D be as accurate as Model A,B,C put together?
neural-network image-recognition yolo
neural-network image-recognition yolo
New contributor
New contributor
edited 9 hours ago
pcko1
1,666418
1,666418
New contributor
asked 13 hours ago
Ryu S.Ryu S.
62
62
New contributor
New contributor
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
It depends specially on data size and model capacity.
If the number of data points per category is insufficient, which is frequently the case in reality, a single model for combined categories performs better, since the effect of data shortage will be attenuated by sharing a model among different but related tasks, i.e. shared knowledge. However, we should not forget about the capacity of model, if model capacity is not enough for the combined task, this sharing would backfire as the model spreads its limited capacity across multiple tasks and becomes "jack of all trades, and master of none". Therefore, this approach is favorable if model capacity permits, which is less of a concern for neural networks with flexible size constraints.
If the number of data points per category is sufficient, which is rarely the case, or model capacity is limited (for example, when model performance stops improving when trained on more than 10% of data), single model per category is better since no capacity will be wasted on different (although related) tasks. From a different point of view, although this choice might be less favorable in terms of model accuracy, but it allows parallel development on smaller tasks, i.e. faster production, which could be a justified benefit for the cost we pay in terms of model accuracy.
We can also combine the two approaches, which could be more time-consuming than both. First we train a model on combined categories, then we feed a part (or parts) of the trained model (such as a layer, the final prediction, etc.) to a specific model that will be trained on one category. This is exactly what a pre-trained model does for us, it is trained on a more general task with more data (possibly even a different but related task), and then we use it for a specific task.
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Ryu S. is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48952%2fyolo-what-is-better-multiple-networks-per-label-or-multiple-labels-in-single-n%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
It depends specially on data size and model capacity.
If the number of data points per category is insufficient, which is frequently the case in reality, a single model for combined categories performs better, since the effect of data shortage will be attenuated by sharing a model among different but related tasks, i.e. shared knowledge. However, we should not forget about the capacity of model, if model capacity is not enough for the combined task, this sharing would backfire as the model spreads its limited capacity across multiple tasks and becomes "jack of all trades, and master of none". Therefore, this approach is favorable if model capacity permits, which is less of a concern for neural networks with flexible size constraints.
If the number of data points per category is sufficient, which is rarely the case, or model capacity is limited (for example, when model performance stops improving when trained on more than 10% of data), single model per category is better since no capacity will be wasted on different (although related) tasks. From a different point of view, although this choice might be less favorable in terms of model accuracy, but it allows parallel development on smaller tasks, i.e. faster production, which could be a justified benefit for the cost we pay in terms of model accuracy.
We can also combine the two approaches, which could be more time-consuming than both. First we train a model on combined categories, then we feed a part (or parts) of the trained model (such as a layer, the final prediction, etc.) to a specific model that will be trained on one category. This is exactly what a pre-trained model does for us, it is trained on a more general task with more data (possibly even a different but related task), and then we use it for a specific task.
$endgroup$
add a comment |
$begingroup$
It depends specially on data size and model capacity.
If the number of data points per category is insufficient, which is frequently the case in reality, a single model for combined categories performs better, since the effect of data shortage will be attenuated by sharing a model among different but related tasks, i.e. shared knowledge. However, we should not forget about the capacity of model, if model capacity is not enough for the combined task, this sharing would backfire as the model spreads its limited capacity across multiple tasks and becomes "jack of all trades, and master of none". Therefore, this approach is favorable if model capacity permits, which is less of a concern for neural networks with flexible size constraints.
If the number of data points per category is sufficient, which is rarely the case, or model capacity is limited (for example, when model performance stops improving when trained on more than 10% of data), single model per category is better since no capacity will be wasted on different (although related) tasks. From a different point of view, although this choice might be less favorable in terms of model accuracy, but it allows parallel development on smaller tasks, i.e. faster production, which could be a justified benefit for the cost we pay in terms of model accuracy.
We can also combine the two approaches, which could be more time-consuming than both. First we train a model on combined categories, then we feed a part (or parts) of the trained model (such as a layer, the final prediction, etc.) to a specific model that will be trained on one category. This is exactly what a pre-trained model does for us, it is trained on a more general task with more data (possibly even a different but related task), and then we use it for a specific task.
$endgroup$
add a comment |
$begingroup$
It depends specially on data size and model capacity.
If the number of data points per category is insufficient, which is frequently the case in reality, a single model for combined categories performs better, since the effect of data shortage will be attenuated by sharing a model among different but related tasks, i.e. shared knowledge. However, we should not forget about the capacity of model, if model capacity is not enough for the combined task, this sharing would backfire as the model spreads its limited capacity across multiple tasks and becomes "jack of all trades, and master of none". Therefore, this approach is favorable if model capacity permits, which is less of a concern for neural networks with flexible size constraints.
If the number of data points per category is sufficient, which is rarely the case, or model capacity is limited (for example, when model performance stops improving when trained on more than 10% of data), single model per category is better since no capacity will be wasted on different (although related) tasks. From a different point of view, although this choice might be less favorable in terms of model accuracy, but it allows parallel development on smaller tasks, i.e. faster production, which could be a justified benefit for the cost we pay in terms of model accuracy.
We can also combine the two approaches, which could be more time-consuming than both. First we train a model on combined categories, then we feed a part (or parts) of the trained model (such as a layer, the final prediction, etc.) to a specific model that will be trained on one category. This is exactly what a pre-trained model does for us, it is trained on a more general task with more data (possibly even a different but related task), and then we use it for a specific task.
$endgroup$
It depends specially on data size and model capacity.
If the number of data points per category is insufficient, which is frequently the case in reality, a single model for combined categories performs better, since the effect of data shortage will be attenuated by sharing a model among different but related tasks, i.e. shared knowledge. However, we should not forget about the capacity of model, if model capacity is not enough for the combined task, this sharing would backfire as the model spreads its limited capacity across multiple tasks and becomes "jack of all trades, and master of none". Therefore, this approach is favorable if model capacity permits, which is less of a concern for neural networks with flexible size constraints.
If the number of data points per category is sufficient, which is rarely the case, or model capacity is limited (for example, when model performance stops improving when trained on more than 10% of data), single model per category is better since no capacity will be wasted on different (although related) tasks. From a different point of view, although this choice might be less favorable in terms of model accuracy, but it allows parallel development on smaller tasks, i.e. faster production, which could be a justified benefit for the cost we pay in terms of model accuracy.
We can also combine the two approaches, which could be more time-consuming than both. First we train a model on combined categories, then we feed a part (or parts) of the trained model (such as a layer, the final prediction, etc.) to a specific model that will be trained on one category. This is exactly what a pre-trained model does for us, it is trained on a more general task with more data (possibly even a different but related task), and then we use it for a specific task.
answered 10 hours ago
EsmailianEsmailian
2,921319
2,921319
add a comment |
add a comment |
Ryu S. is a new contributor. Be nice, and check out our Code of Conduct.
Ryu S. is a new contributor. Be nice, and check out our Code of Conduct.
Ryu S. is a new contributor. Be nice, and check out our Code of Conduct.
Ryu S. is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48952%2fyolo-what-is-better-multiple-networks-per-label-or-multiple-labels-in-single-n%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown