신진우 교수

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any p

The problem of detecting whether a test sample is from in-distribution (i.e.,\ntraining distribution by a classifier) or out-of-distribution sufficiently\ndifferent from it arises in many real-world machine learning applications.\nHowever, the state-of-art deep neural networks are known to be highly\noverconfident in their predictions, i.e., do not distinguish in- and\nout-of-distributions. Recently, to handle this issue, several threshold-based\ndetectors have been proposed given pre-trained ne

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, we distill the predictive distribution between different samples of the same label during training. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network (i.e., a self-knowledge distillation) b

The popularity of Aloha-like algorithms for resolution of contention between multiple entities accessing common resources is due to their extreme simplicity and distributed nature. Example applications of such algorithms include Ethernet and recently emerging wireless multi-access networks. Despite a long and exciting history of more than four decades, the question of designing an algorithm that is essentially as simple and distributed as Aloha while being efficient has remained unresolved.

Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation. In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Specifi

In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples (e.g., images) from more-frequent classes. This simple approach enables a classifier to learn more generalizable features of minority classes, by transferring and leveraging the diversity of the ma

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than cross-entropy based methods which rely on task-specific supervision. In this paper, we found that the similar holds in the continual learning context: contrastively learned representations are more robust against the catastrophic forgetting than ones trained with the cross-entropy objective. Based on this novel observation, we propose a rehea

This paper provides proofs of the rate stability, Harris recurrence, and ε-optimality of carrier sense multiple access (CSMA) algorithms where the random access (or backoff) parameter of each node is adjusted dynamically. These algorithms require only local information and they are easy to implement. The setup is a network of wireless nodes with a fixed conflict graph that identifies pairs of nodes whose simultaneous transmissions conflict. The paper studies two algorithms. The first algorithm s

There has recently been considerable interest in design of low-complexity, myopic, distributed and stable scheduling algorithms for constrained queueing network models that arise in the context of emerging communication networks. Here we consider two representative models. One, a queueing network model that captures randomly varying number of packets in the queues present at a collection of wireless nodes communicating through a shared medium. Two, a buffered circuit switched network model for a

Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle this issue, several methods introduce a transfer learning technique in GAN training. They, however, are either prone to overfitting or limited to learning small distribution shifts. In this paper, we show that simple fine-tuning of GANs with frozen lower layer

Recent improvements in deep learning and hardware support offer a new breakthrough in mobile sensing; we could enjoy context-aware services and mobile healthcare on a mobile device powered by artificial intelligence. However, most related studies perform well only with a certain level of similarity between trained and target data distribution, while in practice, a specific user's behaviors and device make sensor inputs different. Consequently, the performance of such applications might suffer in

Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial variations. Recent works on diffusion models have shown their potential to solve this challenge, yet they suffer from severe computation and memory-inefficiency that limit the scalability. To handle this issue, we propose a novel generative model for videos, coined p

This paper resolves a common complexity issue in the Bethe approximation of statistical physics and the sum-product Belief Propagation (BP) algorithm of artificial intelligence. The Bethe approximation reduces the problem of computing the partition function in a graphical model to that of solving a set of non-linear equations, so-called the Bethe equation. On the other hand, the BP algorithm is a popular heuristic method for estimating marginal distribution in a graphical model. Although they ar

This paper resolves a common complexity issue in the Bethe approximation of statistical physics and the belief propagation (BP) algorithm of artificial intelligence. The Bethe approximation and the BP algorithm are heuristic methods for estimating the partition function and marginal probabilities in graphical models, respectively. The computational complexity of the Bethe approximation is decided by the number of operations required to solve a set of nonlinear equations, the so-called Bethe equa