Hwanjun Song

Hwanjun Song

Auto-generated profile, based on publicly available information

Hwanjun Song

Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HSHwanjun Song
Hwanjun Song
MKMinseok Kim
Minseok Kim
DPDongmin Park
Dongmin Park
YSYooju Shin
Yooju Shin
JLJae-Gil Lee
Jae-Gil Lee
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies.

3 January 2023 in The VLDB Journal
Verified
Journal Article
Closed access
PDF file
SWSteven Euijong Whang
Steven Euijong Whang
YRYuji Roh
Yuji Roh
HSHwanjun Song
Hwanjun Song
JLJae-Gil Lee
Jae-Gil Lee

13 May 2024
Verified
Conference Paper
Open access
YNYoungeun Nam
Youngeun Nam
SYSusik Yoon
Susik Yoon
YSYooju Shin
Yooju Shin
MBMinyoung Bae
Minyoung Bae
HSHwanjun Song
Hwanjun Song
BLByung Suk Lee
Byung Suk Lee
In light of the remarkable advancements made in time-series anomaly detection(TSAD), recent emphasis has been placed on exploiting the frequency domain as well as the time domain to address the difficulties in precisely detecting pattern-wise anomalies. However, in terms of anomaly scores, the window granularity of the frequency domain is inherently distinct from the data-point granularity of the time domain. Owing to this discrepancy, the anomaly information in the frequency domain has not been utilized to its full potential for TSAD. In this paper, we propose a TSAD framework, Dual-TF, that simultaneously uses both the time and frequency domains while breaking the time-frequency granularity discrepancy. To this end, our framework employs nested-sliding windows, with the outer and inner windows responsible for the time and frequency domains, respectively, and aligns the anomaly scores of the two domains. As a result of the high resolution of the aligned scores, the boundaries of pattern-wise anomalies can be identified more precisely. In six benchmark datasets, our framework outperforms state-of-the-art methods by 12.0--147%, as demonstrated by experimental results.

1 October 2023
Verified
Conference Paper
Closed access
DJDahuin Jung
Dahuin Jung
DHDongyoon Han
Dongyoon Han
JBJihwan Bang
Jihwan Bang
HSHwanjun Song
Hwanjun Song
We introduce Domain-Adaptive Prompt (DAP), a novel method for continual learning using Vision Transformers (ViT). Prompt-based continual learning has recently gained attention due to its rehearsal-free nature. Currently, the prompt pool, which is suggested by prompt-based continual learning, is key to effectively exploiting the frozen pretrained ViT backbone in a sequence of tasks. However, we observe that the use of a prompt pool creates a domain scalability problem between pre-training and continual learning. This problem arises due to the inherent encoding of group-level instructions within the prompt pool. To address this problem, we propose DAP, a pool-free approach that generates a suitable prompt in an instance-level manner at inference time. We optimize an adaptive prompt generator that creates instance-specific fine-grained instructions required for each input, enabling enhanced model plasticity and reduced forgetting. Our experiments on seven datasets with varying degrees of domain similarity to ImageNet demonstrate the superiority of DAP over state-of-the-art prompt-based methods. Code is publicly available at https://github.com/naver-ai/dap-cl.

4 September 2020 in Machine Learning
Verified
Journal Article
Closed access
PDF file
HSHwanjun Song
Hwanjun Song
SKSundong Kim
Sundong Kim
MKMinseok Kim
Minseok Kim
JLJae-Gil Lee
Jae-Gil Lee

10 June 2024 in Pattern Recognition
Verified
Journal Article
Closed access
HSHwanjun Song
Hwanjun Song
JBJihwan Bang
Jihwan Bang