One motivation for representation learning is that learning algorithms can design features better and faster than humans can. To this end, we hold this challenge that does not explicitly require that entries use representation learning. Rather, we introduce an entirely new dataset and invite competitors from all related communities to solve it. The dataset for this challenge is a facial expression classification dataset that we have assembled from the internet. Because this is a newly introduced dataset, this contest will see which methods are the easiest to get quickly working on new data.
\r\nExample baseline submissions are available as part of the pylearn2 python package available at https://github.com/lisa-lab/pylearn2
\r\nThe baseline submissions for this contest are in pylearn2/scripts/icml_2013_wrepl/emotions
\r\nBecause this task is very easy for humans to do, we will not provide the final test inputs until one week before the contest closes. Preliminary winners will need to release their winning code and demonstrate that they did not manually label the test set. We reserve the right to disqualify entries that may involve any manually labeling of the test set.
\r\nPreliminary winners will need to release their winning code and demonstrate that they did not manually label the test set. We reserve the right to disqualify entries that may involve any manually labeling of the test set.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "Submissions are scored based on their accuracy of predicting which of the seven classes should be assigned to each image.
\r\nDuring the contest, the current test.csv file will be used to provide a public leaderboard. Because this task is very easy for humans to do, we will not provide the final test inputs until 72 hours before the contest closes.
\r\nAfter we provide the final test inputs, teams wishing to be scored for the final competition should run their classifier on the new data and upload a new .csv file before the competition closes. This procedure is intended to discourage manual labeling of test data.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\nKaggle and the competition host have the right to publicly disseminate any entries or models.
\r\n\r\n Winning solutions need to be made available under\r\n a popular OSI-approved license\r\n in order to be eligible for recognition and prize money.\r\n
\r\n\r\n Prizes will be awarded after the winners have posted their solutions to the competition forum.\r\n Winners must post or link to their solutions within seven (7) days of being notified of their winning status.\r\n
\r\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 2 entries per day.
\r\nYou may select up to 5 final submissions for judging.
\r\n\r\n Because the data can be manually decoded and thus an entry can be created by hand, scoring data will be withheld until you have locked down a model.\r\n
\r\n\r\n You must upload all kernels and model files alongside documentation in a single zip file\r\n in order for your entry to be eligible. You can do this at the time of submission, or append\r\n it to your submission at a later time (before the competition end).\r\n
\r\nStart Date: 4/12/2013 11:10 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 5/24/2013 11:59 PM UTC
\r\n\t\r\nThe organization will not claim any intellectual property from the winning team.
\r\nPeople affiliated with Google and with Université de Montréal may enter the contest, but no one who participated in the creation of the dataset may do so. People affiliated with Google are not eligible for prize money. People involved in the creation of the dataset are forbidden to give any advice regarding the contest to any of the competitors.
\r\nYou may use additional training data, but please restrict yourself to publicly available datasets. Do not manually label the test data and train your classifier on it.
\r\nYou do not need to use a representation learning algorithm. Algorithms that use hand-designed features such as HOG, SIFT, etc. are perfectly acceptable, as are algorithms that augment the dataset with synthetic transformations. However, your final system must be able to autonomously classify the test data without a human in the loop.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "The data consists of 48x48 pixel grayscale images of faces. The faces have been automatically registered so that the face is more or less centered and occupies about the same amount of space in each image. The task is to categorize each face based on the emotion shown in the facial expression in to one of seven categories (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral).
\r\ntrain.csv contains two columns, \"emotion\" and \"pixels\". The \"emotion\" column contains a numeric code ranging from 0 to 6, inclusive, for the emotion that is present in the image. The \"pixels\" column contains a string surrounded in quotes for each image. The contents of this string a space-separated pixel values in row major order. test.csv contains only the \"pixels\" column and your task is to predict the emotion column.
\r\nThe training set consists of 28,709 examples. The public test set used for the leaderboard consists of 3,589 examples. The final test set, which was used to determine the winner of the competition, consists of another 3,589 examples.
\r\nThis dataset was prepared by Pierre-Luc Carrier and Aaron Courville, as part of an ongoing research project. They have graciously provided the workshop organizers with a preliminary version of their dataset to use for this contest.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "Post-Competition Wrapup
\r\nChallenges in Representation Learning ICML 2013 Workshop
\r\nThis contest is associated with the ICML 2013 Workshop on Representation Learning.
\r\nFirst prize: $350 and an invitation to speak at the workshop.
\r\nSecond prize: $150
\r\nWe encourage submission of papers to the workshop. Scientifically interesting papers will be accepted regardless of performance in the contest.
\r\nThe funding for the prizes was generously provided by Google, Inc.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }