Comments (3)
(1): Computing the focal loss for a single class introduces some noise which we found to be less if we increase the number of classes. The number 20 is a bit arbitrary here.
(2): We mention the multi-frame attention in the implementation details. However, since it is not a key element of our contribution and how track queries work we did not provide an in-depth discussion. In particular, the identity preservation (IDF1 and ID switches) benefit a lot from this.
from trackformer.
Hi @timmeinhardt ,
Thanks for your great works!
I found that the number of classes is added by 1 during the definition of classifier.
At the post process, the last appended class is only removed at this line. But the computation of loss does not remove this appended class.
trackformer/src/trackformer/models/detr.py
Line 476 in d62d810
I am curious why you do such settings. Does this have a influence on the tracking performance.
Another question is that the model is optimized with focal loss, which means that sigmoid is used to activate the predicted logits. However, in the post process, softmax is adopted to acitvate the logits and get the prediction scores. Is this a bug or designed by your experimental findings?
from trackformer.
The additional class is added for background prediction in the original DETR formulation. This means also including the class in the loss. However, when running with focal loss, i.e., in the deformable DETR formulation, we do not add the additional class. See this line where we subtract from the number of classes for focal loss
Your second question is also related to the difference between DETR and Deformable DETR. When running the latter with focal loss we do not apply a softmax in the post processing. See this module:
from trackformer.
Related Issues (20)
- Loading Data for Tracking HOT 7
- Error while training custom dataset, in validation phase: HOT 3
- how to display the ID numbers HOT 1
- Problems with the MOT17 dataset when testing HOT 1
- Unknown CUDA arch (8.6) or GPU not supported HOT 1
- The MOTP metrics is showing a low score. HOT 5
- Issues related to track IDs HOT 8
- Why num_classes=20 in r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint_hidden_dim_288.pth? HOT 2
- The generation of trackid
- Will the detection performance such as AP50 increase after tracking?
- Unexpected Random Track Prediction
- installation issues HOT 1
- "Training on MOT17, the parameters are incorrect."
- How to use finetuned model for tracking?
- Pretrained weight files
- About targets at training HOT 1
- About MOT dataset PREV HOT 4
- How to Prepare Custom Dataset for TrackFormer Multi-Object Tracking with COCO-Style Annotations? HOT 2
- generate_coco_from_mot script does not converts SDP and DPM sequences from MOT17 HOT 1
- Linker error during installation of MultiScaleDeformableAttention
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 trackformer.