Comments (4)
@liuziwei7 thanks for your clarifications! We are actually working on a similar project and we obtained the same observations. I really like (and agree with) the approach of tackling open long-tailed recognition problems with a single framework. It is still an ongoing project but we were able to obtain good results with a theory-driven input sampling (without attention, hallucinator, etc). We will try our algorithm on your framework. Thanks again!
from openlongtailrecognition-oltr.
@matttrd Thanks for asking. The plain was only trained for 30 epochs and the rest of the methods were trained for 90 epochs. As discussed here: #4 (comment) , more epochs would not help the performance of plain model since it was already converged around 30 epochs.
from openlongtailrecognition-oltr.
@zhmiao thanks for answering. Probably I'm missing something but I trained (using your code) the plain model (stage 1) with 90 epochs with the usual drop of the learning rate every 30 epochs getting 32.7% of overall top1 test accuracy and:
- few shot: 4%
- Median: 23.9%
- Many: 53.6%
I understand that the loss converges around 30 epochs but this is true only if you let the LR drop every 10 epochs as you did. I think this should be the fair comparison. Am I wrong?
from openlongtailrecognition-oltr.
Thanks for reporting these results! Actually we have obtained some similar observations in our follow-up project.
A model trained on long-tailed dataset has some interesting behavior change with different initializations and epoches:
- Large learning rate tends to make the model bias to many-shot classes;
- Intermediate and late epoches are critical for the performance of few-shot classes.
We speculate the root of these phenomena come from the learning dynamics of long-tail-trained models. Therefore, we are considering update our manuscript to report a sequence of snapshot accuracies instead of a single final accuracy. It is yet an open question, and we believe it is definitely an interesting direction to further investigate.
Our aim of the open long-tailed recognition paper is to formally define and make clear this important real-world problem, instead of providing a silver-bullet solution. We welcome everyone to work on this topic and further improve the underlying approaches :)
from openlongtailrecognition-oltr.
Related Issues (20)
- Reproducing OLTR results HOT 3
- Stage 2 multi GPU
- why fix all parameters except self attention parameters? HOT 4
- Table 2 results HOT 2
- Pretrained Weights for Places_LT?
- the use of fc layer HOT 2
- the accuracy of the train and val HOT 2
- how to compute centroids?
- Why the input dimension of the `fc_spatial` layer in `ModulatedAttLayer` is 7*7*in_channel? HOT 1
- Many_shot_accuracy_top1: nan on my own dataset HOT 1
- Revised F-measure results for other models in your paper
- Applications for face recognition
- Error when running stage_1.py under Places_LT
- Unable to reproduce baseline result on ImageNet-LT HOT 1
- BUG: stage1 test error!!
- Could you please give me an example of arranging ILSVRC2014 dataset? HOT 7
- Implementation on Inat-18
- About Class aware sampler
- The role of untrained FC(add_fc)
- The question about the version of Places_LT
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 openlongtailrecognition-oltr.