![](https://images.aicrowd.com/images/participants/image_file/18894/moto.jpg)
Location
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Advanced Building Control & Grid-Resilience
Latest submissions
Understand semantic segmentation and monocular depth estimation from downward-facing drone images
Latest submissions
What data should you label to get the most value for your money?
Latest submissions
See Allgraded | 177196 | ||
failed | 177195 | ||
graded | 177192 |
Behavioral Representation Learning from Animal Poses.
Latest submissions
See Allgraded | 186662 | ||
graded | 186659 | ||
graded | 186360 |
Airborne Object Tracking Challenge
Latest submissions
See Allgraded | 153702 | ||
graded | 153698 | ||
graded | 153678 |
ASCII-rendered single-player dungeon crawl game
Latest submissions
See Allgraded | 150030 | ||
graded | 150025 | ||
graded | 148030 |
Latest submissions
Machine Learning for detection of early onset of Alzheimers
Latest submissions
See Allgraded | 143382 | ||
graded | 143379 | ||
graded | 143378 |
3D Seismic Image Interpretation by Machine Learning
Latest submissions
Play in a realistic insurance market, compete for profit!
Latest submissions
See Allgraded | 127187 | ||
graded | 127178 | ||
graded | 126085 |
A benchmark for image-based food recognition
Latest submissions
See Allgraded | 116233 | ||
graded | 116232 | ||
graded | 116215 |
Latest submissions
Latest submissions
See Allgraded | 128320 | ||
graded | 128212 |
5 Puzzles, 3 Weeks | Can you solve them all?
Latest submissions
Participant | Rating |
---|---|
![]() |
149 |
Participant | Rating |
---|
-
moto_jsato ADDI Alzheimers Detection ChallengeView
-
ClintoMoto NeurIPS 2021 - The NetHack ChallengeView
-
moto Airborne Object Tracking ChallengeView
-
funGPT HackAPrompt 2023View
ESCI Challenge for Improving Product Search
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Simple baseline with simple transformer
Over 2 years agoLooking at the provided baseline, I found it hard to follow. Therefore I decided to publish my simple baseline.
Not all data were used nor any fine-tune has been done.
It just took more than 1 hour for training and 15 minutes for inference.
Hope it helps newcomers to understand the data and the problem.
Data Purchasing Challenge 2022
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Purchase with anomaly detection
Over 2 years agoNot so sure why the discussion is somehow quiet in round 2. I am sharing my first success.
I love anomaly detection so I tried to apply it here. It has been quite surprise that few tries have even worse result than the random purchase.
However, I finally manage to beat the random purchase. Insight could be found here
AIcrowd | Purchase with anomaly detection | Posts.
Please give me a vote for my hard work
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
:aicrowd: [Update] Round 2 of Data Purchasing Challenge is now live!
Over 2 years agoMany thanks for your quick reply.
βYou will still have to train your models from scratchβ => Could we use pre-trained weights as in round 1 ?
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
:aicrowd: [Update] Round 2 of Data Purchasing Challenge is now live!
Over 2 years ago@snehananavati : Many thanks for your update. As far I understood, we actually donβt need to provide code for the training phase and the prediction phase. The system will use the same training pipeline - B4 with 10 epochs and then generate predictions and the scores by itself.
In other words, we only need to focus on the purchase phase. Do I understand correctly ?
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
0.9+ Baseline Solution for Part 1 of Challenge
Over 2 years agoOh, I missed this thread. Many thanks for your sharing @mark_haoxiang . It is quite interesting that the simple approach works well.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
[Notebooks & Resource] Community Contributions and Baselines
Over 2 years agoI would like to mention 2 baselines.
My own baseline - score 0.84 AIcrowd Submission Received #174462 - v0p5 (#4) Β· Issues Β· moto / data-purchasing-optimization Β· GitLab.
My new baseline based on Leocdβs code - score 0.885
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Experiments with βunlabelledβ data
Over 2 years ago@sergey_zlobin : Thanks for your information.
I am wondering if you tried to purchase all 10K then what the score could be.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Tensorflow/Keras folks, you are not being left behind in this competition
Over 2 years ago@huynhngoc : Many thanks. I did not know that we could access labels_df.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Pseudo-labeling
Over 2 years agoIndeed. I donβt see why we canβt use pseudo-labels. One of the naive approach for the purchase policy is to predict all images. 1) If the confidence is high => use the pseudo-label 2) if the confidence is low => purchase the label.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Baseline 0.84
Over 2 years agoIn order to support my request (Request to have the same baseline for everyone!), I shared my baseline with densenet. You could access the submission at AIcrowd Submission Received #174462 - v0p5 (#4) Β· Issues Β· moto / data-purchasing-optimization Β· GitLab.
If my submission can access the pre-trained weights for efficient net B6 from https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/, it could score 0.87+.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Request to have the same baseline for everyone!
Over 2 years agoDear organizer, all,
This challenge is a data-centric competition and the main purpose is to optimize the purchase. However, given our experiments the upper bound for the purchase policy is less than 3%. It means that we need to have a good baseline before we could work on the purchase policy.
Therefore, in my opinion, we should share the same training procedure. Our customer DL pipeline is only to optimize the purchase. I know it would be unfair for the current top teams but it would drive the competition in the way it should be.
Well, I am sharing my baseline with densetnet. It scores 0.84. The same pipeline with B6 could get 0.87+ (however, the pre-trained weights are not from the official site). The code is here AIcrowd
If it is impossible to force all participants, please allow us to use weights from other popular sources! I will try to publish a baseline 0.88+ so that people could focus more on the purchase optimization.
Many thanks.
M
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
The mystery of 0.489 and how to beat 2 deep-learning baselines with a single line of code
Over 2 years agoIf you look at my notebook AIcrowd | Baseline + Exploration: random purchase vs full purchase | Posts you could see that the zero-prediction solution got a score of 0.478 locally.
And that solution will score 0.489 in the LB, beating 2 public baselines.
- Video tutorial of challenge and how to submit first baseline with 0.44 on LB
- Baseline submission - #3 by moto
How to do that, just replace
by
np.zeros(4).astype(int)
Thatβs it.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Baseline submission
Over 2 years agoUpdate: The code is now using pre-trained weights. It has a better score now.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Baseline submission
Over 2 years agoI am very happy to share my baseline Files Β· submission-v0p1p5 Β· moto / data-purchasing-hello Β· GitLab
The most challenging job is to use both 2 datasets (5K+3K) to train a model.
Note that the low score might be due to the fact that I havenβt included the pre-trained weights. Just submitted that one.
Right now, you guys could focus on
- DL techniques such as different augmentations, network archs, schedulers β¦
- Optimize purchase
Enjoy.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
What did you get so far?
Over 2 years agoGuys in the LB are fast but not me. I still need to understand how to submit.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
What did you get so far?
Over 2 years agoI guess you guys havenβt been able to defeat the random purchase
My experiment showed that 10K purchase is only a little bit better than 3K random purchase (https://www.aicrowd.com/showcase/exploration-random-purchase-vs-full-purchase). So, it is super hard to beat the random purchase.
Updated:
- The new link is https://www.aicrowd.com/showcase/baseline-exploration-random-purchase-vs-full-purchase
- The same code is included in my baseline
Files Β· submission-v0p1p5 Β· moto / data-purchasing-hello Β· GitLab
Airborne Object Tracking Challenge
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
π¨ Baseline released, SiamMOT: Siamese Multi-Object Tracking
About 3 years ago@shivam: any way to run the baseline in colab for local validation ?
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
Max Number of Submissions?
About 3 years ago@shivam: I am unable to submit today after 1 failed submission.
![](https://images.aicrowd.com/100x100/images/participants/image_file/18894/moto.jpg)
π¨ Clarification: Which are valid submissions?
About 3 years ago@shivam: Many thanks for your quick reply.
Does it also mean using historical frames is accepted ?
Notebooks
-
Purchase with anomaly detection Using anomaly scores to select images to buy labelsmotoΒ· Over 2 years ago
-
Best baseline in round 1 - score 0.885 Best baseline in round 1 - score 0.885motoΒ· Over 2 years ago
-
Baseline + Exploration: random purchase vs full purchase Exploration: random purchase vs full purchasemotoΒ· Over 2 years ago
-
Simple EDA and Baseline - LB 0.66 (0.616 with a magic) Simple EDA and Baseline - LB 0.66 (0.616 with a magic)motoΒ· Over 3 years ago
Simple baseline with simple transformer
Over 2 years agoFor task 3, it is 0.538.
PS: I am happy with this score given the fact that I only trained for 2 epochs with only limited number of rows.