Comments (4)
Thank you for your interest in our work!
Regarding the configurations, we will release all hyperparameter settings for Table 1 and 6 within a month. Sorry for the inconvenience.
Regarding the evaluation metric, we are aware that most existing works primarily evaluate their methods with the Top-1 Loc
metric. However, we believe that Top-1 Loc
is insufficient to make claims about improved localization. A technique can potentially see an improvement in Top-1 Loc
just by having significantly better classification (even with worse localization!). We believe that any localization claims would have to be validated by more explicit localization-centric metrics. In this regard, PxAP
with mask annotations is the ideal metric for evaluating WSOL. However, in many cases, only the box annotations are available. In this case, we suggest using MaxBoxAcc
. Please see Sec. 3 and 4 for more detail.
However, as you mentioned, Top-1 Loc
is a widely used metric in WSOL literature, so we reported them in Appendix Table 6. We will also include classification accuracies in the revised version.
from wsolevaluation.
Appreciate for your reply.
Would it be possible to release the configs at least for MaxBoxAcc for CAM on CUB and Imagenet as well as Top-1 Loc for ACoL on CUB and Imagenet? It would be highly appreciated!
Also, for CUBV2, I realized 059. California_Gull only has 3 images. Does this mean the maximum value for num_val_sample_per_class is 3 for CUB?
Thank you
from wsolevaluation.
Some classes include less than five images. Currently, our implementation does not support 4
or 5
for CUB dataset. Instead, you can use all images in train_fullsup
by setting num_val_sample_per_class
to 0
.
Here are the configs:
CAM on CUB (epochs 50, lr_decay_frequency 15)
vgg: lr (0.00003562485), large_feature_map (False)
resnet: lr (0.00025028018), large_feature_map (True)
inceptionv3: lr (0.00051145010), large_feature_map (True)
CAM on ImageNet (epochs 10, lr_decay_frequency 3)
vgg: lr (0.00010902234), large_feature_map (False)
resnet: lr (0.00015072583), large_feature_map (True)
inceptionv3: lr (0.00012730641), large_feature_map (True)
ACoL on CUB (epochs 50, lr_decay_frequency 15)
resnet: lr (0.00015396656), large_feature_map (True), acol_threshold (0.64)
vgg: lr (0.00000349871), large_feature_map (True), acol_threshold (0.76)
inceptionv3: lr (0.00721313070), large_feature_map (True), acol_threshold (0.79)
ACoL on ImageNet (epochs 10, lr_decay_frequency 3)
resnet: lr (0.00035247105), large_feature_map (True), acol_threshold (0.81)
vgg: lr (0.00047688934), large_feature_map (True), acol_threshold (0.95)
inceptionv3: lr (0.00046360434), large_feature_map (True), acol_threshold (0.81)
from wsolevaluation.
I see. Thank you for the clarification and configs!
from wsolevaluation.
Related Issues (20)
- cannot reproduce the results using CAM-Inception on CUB dataset HOT 1
- ImagenetV2 has a lot of incorrect Bbox annotation information? HOT 4
- logic problem HOT 3
- Data split for FSL HOT 2
- About ImageNetV2 file name HOT 7
- About FSL baseline HOT 2
- Dataset Structure HOT 2
- Cropping and Resizing HOT 2
- optimal oracle value HOT 1
- Interpretation of the result HOT 3
- FSL baseline HOT 1
- openimages pxap perf changed between maxboxacc and maxboxaccv2. why? HOT 2
- Top-1 localization HOT 1
- Inconsistent annotations between metadata and source data in CUB test? HOT 1
- slow cv2.findContours HOT 3
- Sequence of normalization and resize of CAM? HOT 1
- The results in the table are inconsistent with the paper
- Results of OpenImage30K
- Pretrained Models
- Inception v3 different than Pytorch implementation
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 wsolevaluation.