Comments (3)
You've raised a good question. Batch Normalization (BN) plays a supportive role here by aiming to estimate the mean and variance of the feature distribution. In practice, statistical methods can also be employed to obtain the mean and variance of features. The selection of hyperparameters is indeed quite subtle, as I've observed that optimal hyperparameters vary across different models. I would like to share with you another piece of our work titled "Rethinking Out-of-Distribution Detection From a Human-Centric Perspective" (https://arxiv.org/abs/2211.16778). This work indicates that the algorithm's performance is significantly influenced by the model structure and parameters. This observation might explain why optimal hyperparameters differ across various models. It also reveals the current difficulty in constructing a cross-model universal detection algorithm. I hope my response proves helpful.
If you have any further questions, please feel free to email me at [email protected] or chat with me on WeChat.
from easyrobust.
Thanks for your reply! It helps me a lot.
Indeed, using statistical methods to obtain the mean and variance of features can be more practical. I think perhaps using quantiles instead of mean/variance might be also a good choice. Of course, there might be more suitable statistics.
I quite agree with your viewpoint in "Rethinking Out-of-Distribution Detection From a Human-Centric Perspective" that "model architectures and training regimes matter in OOD detection and should be considered integral when designing new detection methods." Perhaps future OOD detection methods require insensitive hyperparameters (if any), or can reveal the relationship between hyperparameters and network architectures/model training.
from easyrobust.
I agree with you. After realizing the significant impact of the model’s parameters on detection algorithms, I have been recently reflecting on whether there are algorithms that are insensitive to hyperparameters or even delving into how much contribution post-hoc detection methods make to security. Feel free to contact me for further discussion.
from easyrobust.
Related Issues (19)
- Some questions! HOT 2
- Can you provide the training code for DRA please? HOT 1
- Inference of DAT model HOT 4
- Problem of calculating regional gini index in easyrobust/examples/attacks/inequality/inequality_test.py line 110 HOT 2
- Could not load mae_dat file
- question about visualization in BATS HOT 1
- Questions on reproducing BATS HOT 1
- About the overlap of the visualization of the BATS. HOT 2
- ImageNet Datasets
- I could provide some pretrained model HOT 1
- An issue about the official code for DMMIA in "easyrobust/examples/attacks/dmmia_inversion"
- Re-produce COCO-O results HOT 2
- Getting error while loading checkpoints HOT 4
- How to finetune the DRA model ? HOT 3
- [Submit Model] <convnext_L>
- Where are the codes of dra fine-tuning of the model ? HOT 1
- object det with DAT HOT 5
- Question about BATS HOT 2
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 easyrobust.