Comments (3)
Thanks for your attention to our work!
Yes, you are right. There might be some discrepancies, but we empirically found that patches with higher predicted loss tend to be more discriminative (see Fig. 2, Fig. S1, and Fig. S2).
Revisiting this mismatch can be interesting for future works.
from hpm.
Thanks for your reply!
Another question: Why bother to learn an additional decoder for loss prediction? Why don't you just use the original loss of reconstruction decoder from the teacher model for hard patch mining?
from hpm.
There is no reconstruction loss if we take fully visible images as input.
from hpm.
Related Issues (10)
- question about COCO detection HOT 13
- Question about heatmap HOT 3
- Confused about "model_teacher" in pre-training code HOT 2
- Request for certain experimental matters HOT 2
- Questions Regarding Pretraining Experiment Configuration HOT 1
- Question about pretrain models on 800 epochs HOT 2
- Availability of Pre-trained Models
- 模型大小 HOT 1
- scaler HOT 6
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 hpm.