In this competition, you are provided with a supervised dataset X consisting of the raw content of news articles
and the binary popularity (where 1 means "popular" and -1 not, calculated based on the number of shares in online social networking services) of these articles as labels.
Your goal is to learn a function f from X that is able to predict the popularity of an unseen news article.
ref :https://nthu-datalab.github.io/ml/competitions/Comp_01_Text-Feature-Engineering/01_Text-Feature-Engineering.html
In this competition, you have to train a model that recognizes objects in an image. Your goal is to output bounding boxes for objects.
ref : https://www.kaggle.com/competitions/datalab-cup-2-cnn-for-object-detection/overview
In this work, we are interested in translating text in the form of single-sentence human-written descriptions directly into image pixels. For example, "this flower has petals that are yellow and has a ruffled stamen" and "this pink and yellow flower has a beautiful yellow center with many stamens". You have to develop a novel deep architecture and GAN formulation to effectively translate visual concepts from characters to pixels.
ref :https://www.kaggle.com/c/datalab-cup3-reverse-image-caption-2022f
In this work, we try to crack the unlearnable dataset which proposed by Neural Tangent Generalization Attacks (NTGA) ICML'21
Authors of NTGA propose the generalization attack, a new direction for poisoning attacks, where an attacker aims to modify training data in order to spoil the training process such that a trained network lacks generalizability. They devise Neural Tangent Generalization Attack (NTGA), a first efficient work enabling clean-label, black-box generalization attacks against Deep Neural Networks.
ref: