Loading
0 Follower
0 Following
fkemeth

Location

DE

Badges

2
0
0

Activity

Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Latest submissions

No submissions made in this challenge.

Latest submissions

See All
graded 244935

Small Object Detection and Classification

Latest submissions

See All
graded 240474
failed 240454
failed 240438

Latest submissions

See All
failed 210395
failed 210392
failed 210264

Latest submissions

No submissions made in this challenge.

Predicting smell of molecular compounds

Latest submissions

No submissions made in this challenge.

Latest submissions

See All
graded 21049
graded 13494

Latest submissions

No submissions made in this challenge.
Participant Rating
Participant Rating

MosquitoAlert Challenge 2023

Submission failed during Inference

6 months ago

In the validation phase, we have inference times of around 1s. So I assume the reason is that there are higher-res images in the test data, could that be?

Submission failed during Inference

6 months ago

@dipam the submission codes are

#238089 #238088 #238030 #238029

Submission failed during Inference

6 months ago

Hi @dipam, can you have a quick look at this? We really are stuck since Mosquitoalert Validation runs through but Mosquitoalert Prediction does not, and we do not have any informative error logs.

πŸ’¬ Feedback & Suggestions

8 months ago

Thank you for organizing this competition!

I would like to provide feedback on the ground truth bounding boxes.

I compared the ground truth bounding boxes of the training data against the bounding boxes of a pre-trained model called Owl-ViT, and below are some issues which, as I am convinced, adversely effect the quality of the competition:

Bounding Box Quality
In some cases, the quality of the ground truth bounding boxes are bad, leading to low IoU between the ground truth and Owl-ViT, although Owl-ViT arguably leads to better bounding boxes. In those cases the IoU between the two boxes would even be below the required threshold for scoring.
image

image

image

image

Multiple Objects in One Image
In case of multiple objects, sometimes the ground truth bounding box is around the smaller object. I argue that one should either split those images in two such that no image contains more than one object, or have the ground truth around the largest object.
image

Bounding Boxes Around Multiple Objects

From my point of view, each ground truth bounding box should be around one object only.
image

Since the challenge metric involves thresholding the IoU between the predicted and (arguably bad) ground truth bounding boxes, I fear the scope of the challenge might change from trying to locate mosquitos as best as possible to reproducing the ground-truth bounding boxes as best as possible to achieve a good challenge score.

I therefore suggest to update the ground truth bounding boxes, or adjust the challenge metric as to not include the IoU.

fkemeth has not provided any information yet.