In this paper, we present a comprehensive review of the imbalance problems in object
detection. To analyze the problems in a systematic manner, we introduce a problem-based …

We consider the problem of zero-shot recognition: learning a visual classifier for a category
with zero training examples, just using the word embedding of the category and its …

Federated Learning (FL) has recently received significant interests thanks to its capability of
protecting data privacy. However, existing FL paradigms yield unsatisfactory performance for …

Deep embeddings answer one simple question: How similar are two images? Learning
these embeddings is the bedrock of verification, zero-shot learning, and visual search. The …

Thanks to the recent developments of Convolutional Neural Networks, the performance of
face verification methods has increased rapidly. In a typical face verification method, feature …

The modern image search system requires semantic understanding of image, and a key yet
under-addressed problem is to learn a good metric for measuring the similarity between …

Zero-shot learning (ZSL) models rely on learning a joint embedding space where both
textual/semantic description of object classes and visual representation of object images can …

Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due
to the missing counterfactuals and the selection bias. Existing ITE estimation methods …

The objective of deep metric learning (DML) is to learn embeddings that can capture
semantic similarity information among data points. Existing pairwise or tripletwise loss …

Data for face analysis often exhibit highly-skewed class distribution, ie, most data belong to
a few majority classes, while the minority classes only contain a scarce amount of instances …