Comments (4)
Thank you for the interest in our work! and you are correct in assuming that we want to generate the onebox dataset with this inversion process.
By default, we set args.real_mixin_alpha=0.0
over here:
Line 256 in 80a396d
This makes sure that the initialization consists of only random noise i.e the expression becomes:
init = 0.0*imgs + (1.0 - 0.0)*init
This argument was added because we were curious to explore what the model inversion process generates when initialized with something other than random noise. An example of such an initialization would be using bounding boxes and corresponding images from a real dataset such as COCO or Pascal's VOC0712. In this scenario, we can use args.real_mixin_alpha
to control how much of the initialization is close to the original image.
from diode.
Thank you for the interest in our work! and you are correct in assuming that we want to generate the onebox dataset with this inversion process.
By default, we set
args.real_mixin_alpha=0.0
over here:Line 256 in 80a396d
This makes sure that the initialization consists of only random noise i.e the expression becomes:
init = 0.0*imgs + (1.0 - 0.0)*init
This argument was added because we were curious to explore what the model inversion process generates when initialized with something other than random noise. An example of such an initialization would be using bounding boxes and corresponding images from a real dataset such as COCO or Pascal's VOC0712. In this scenario, we can useargs.real_mixin_alpha
to control how much of the initialization is close to the original image.
Thank you for your detailed reply, and I got it. So, are the evaluation results in your paper based on an initialization with a real dataset or not ?
Another question is about Table 3. The top and the bottom rows are the results by using original and generated images & lables, respectively, and both are quite clear. My confusion comes from the middle row. You mentioned that it is by using synthetic images conditioned on MS-COCO labels. However, MS-COCO labels contains multiple objects for each image, and how did you use these labels to generate corresponding images ?
Looking forward to your reply !
from diode.
-
The evaluation results in our paper are based on using random noise as initialization for the DIODE generation process i.e
args.real_mixin_alpha
was always set to 0.0. -
In middle row of Table 3, you are correct that we use multiple object labels for each image when we sample labels from coco. This is because our object detection network Yolo-V3 and its loss function allow predicting multiple objects per image. Hence, during the inversion process, we can condition on multiple bboxes for every image.
In fact, we use the ability to condition on multiple bboxes as part of a unique bbox sampling procedure called false positive sampling (FP sampling). In FP sampling, we discover that during the image generation process, network constantly tries to add context to the image i.e if we condition on a road bike, we often get to see a human generated close to it. To use this unique ability, we aggregate high confidence false positive detections that appear during the generation process leading to more realistic initialization bboxes and generated images. See section 3.1, 5.2 and figure 3.
from diode.
- The evaluation results in our paper are based on using random noise as initialization for the DIODE generation process i.e
args.real_mixin_alpha
was always set to 0.0.- In middle row of Table 3, you are correct that we use multiple object labels for each image when we sample labels from coco. This is because our object detection network Yolo-V3 and its loss function allow predicting multiple objects per image. Hence, during the inversion process, we can condition on multiple bboxes for every image.
In fact, we use the ability to condition on multiple bboxes as part of a unique bbox sampling procedure called false positive sampling (FP sampling). In FP sampling, we discover that during the image generation process, network constantly tries to add context to the image i.e if we condition on a road bike, we often get to see a human generated close to it. To use this unique ability, we aggregate high confidence false positive detections that appear during the generation process leading to more realistic initialization bboxes and generated images. See section 3.1, 5.2 and figure 3.
Very clear, thanks for your reply !
from diode.
Related Issues (17)
- Bad results of generating images of KITTI dataset HOT 8
- [GCS] Access to directory DIODE_data HOT 3
- [GCS]need access to data HOT 3
- Does this method used for a two-stage object detector? HOT 2
- [GCS] access to data HOT 2
- Image variance collapses to zero HOT 1
- About L2 & TV loss, mean value HOT 1
- Question about the pretrained model. HOT 1
- Training time consumption HOT 1
- ERROR occurs when doing distillation!! help!
- [GCS]Access to data
- Same content in label files on bdd100k dataset HOT 2
- Regarding training using BDD100K dataset HOT 9
- Re: Self-similarity hook HOT 3
- [IMPORTANT][GCS] Access to Google's cloud storage bucket
- Try on two stage detector 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 diode.