Comments (3)
Hi, I think you are referring to the sparse supervision with a sinkhorn matching layer. For the sinkhorn case, a negative sample (an unmatchable grid) should lead to high confidence or score in the dustbin entry, thus it is actually a positive sample for the dustbin entry. The "positive" and "negative" samples here are different from ones defined in the RetinaNet. They are just positive samples corresponding to different matching targets. Moreover, you might find the alpha
term confusing too since both "positive" & "negative" samples use alpha
without one of them assigned 1 - alpha
weight for neg-pos balancing. We actually use POS_WEIGHT
& NEG_WEIGHT
in the config for neg-pos balancing, which makes the alpha
term meaningless. The naming could be a little bit confusing. I would try to refactor that part in the future😀.
from loftr.
Thanks. I still don't fully understand. As I understand the dustbin scores(S_sudtbin). If a S_sudtbin has a high score, that menas unmatched couple predict a high score. But we need unmatched coupe has a low score. So the Loftr should decrease the S_dustbin. In other words, S_dusstbin Is inversely proportional to Loss.
Can you point out what's wrong with my understanding.
Thank you
from loftr.
For the sparse supervision with a sinkhorn matching layer, you could approximately think of it as a multi-class classification problem, like a softmax-focal-loss
instead of sigmoid-focal-loss
. For each coarse-level grid in the left view to be matched, there is one "target" in the right view that corresponds to it. This "target" could be a grid in the right view or just a dustbin (unmatchable). We extract those entries from the score matrix and apply focal-loss to them, whose scores/probabilities should be high instead of low, as you said. Maybe just forget about the positive & negative terms; we only supervise the positive terms in the sparse supervision case. The sinkhorn layer could naturally suppress the negative terms (which should have low scores).
from loftr.
Related Issues (20)
- Tensorboard visualization - are the indices correct?
- About train with fp16
- About the dataset indices of Megadepth HOT 2
- How to train the model for HPatches
- train model for image matching
- training on custom dataset HOT 4
- Can the model be limited to detecting key points in a region of interest?
- h5py can't read data
- meet an error when training loftr: EOFError: Ran out of input HOT 3
- image size
- Bug found in supervision process
- main_cfg problem
- How to train LoFTR on custom dataset?
- megadepth_indices下载不下来 HOT 1
- How to get image feature maps from the pretrained model?
- My dataset is only RGB, can I use it for training?
- ScanNet Training Pairs
- File "h5py\h5f.pyx", line 96, in h5py.h5f.open OSError: Unable to open file
- COLMAP dumps for Megadepth 1500 dataset
- to reproduce the training,have to download MegaDepth_v1?199G dataset? HOT 1
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 loftr.