Hwanjun Song

2.1k total citations · 1 hit paper
40 papers, 932 citations indexed

About

Hwanjun Song is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Information Systems. According to data from OpenAlex, Hwanjun Song has authored 40 papers receiving a total of 932 indexed citations (citations by other indexed papers that have themselves been cited), including 28 papers in Artificial Intelligence, 12 papers in Computer Vision and Pattern Recognition and 5 papers in Information Systems. Recurrent topics in Hwanjun Song's work include Natural Language Processing Techniques (8 papers), Topic Modeling (7 papers) and Machine Learning and Data Classification (7 papers). Hwanjun Song is often cited by papers focused on Natural Language Processing Techniques (8 papers), Topic Modeling (7 papers) and Machine Learning and Data Classification (7 papers). Hwanjun Song collaborates with scholars based in South Korea, Canada and United States. Hwanjun Song's co-authors include Jae-Gil Lee, Minseok Kim, Yooju Shin, Wook-Shin Han, Minseok Kim, Se-Young Yun, Jihwan Bang, Doyoung Kim, Dongyoon Han and Jonghyun Choi and has published in prestigious journals such as Pattern Recognition, IEEE Transactions on Neural Networks and Learning Systems and Machine Learning.

In The Last Decade

Hwanjun Song

30 papers receiving 910 citations

Hit Papers

Learning From Noisy Labels With Deep Neural Networks: A S... 2022 2026 2023 2024 2022 100 200 300 400 500
What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

  1. Learning From Noisy Labels With Deep Neural Networks: A Survey
    2022 568 citations Hwanjun Song, Minseok Kim et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Hwanjun Song South Korea 11 619 269 79 69 69 40 932
Simon Lacoste-Julien Canada 12 850 1.4× 430 1.6× 59 0.7× 41 0.6× 64 0.9× 33 1.2k
Yooju Shin South Korea 4 382 0.6× 162 0.6× 43 0.5× 46 0.7× 30 0.4× 9 605
Yilin Yan United States 10 635 1.0× 352 1.3× 101 1.3× 36 0.5× 122 1.8× 23 1.3k
Xuming Han China 12 311 0.5× 181 0.7× 40 0.5× 35 0.5× 70 1.0× 64 744
M. Arif Wani India 14 228 0.4× 275 1.0× 77 1.0× 78 1.1× 52 0.8× 63 802
Ilya Loshchilov Switzerland 10 618 1.0× 304 1.1× 54 0.7× 26 0.4× 35 0.5× 13 1.0k
Xu Jia China 9 954 1.5× 593 2.2× 48 0.6× 25 0.4× 54 0.8× 17 1.3k
Shaoning Zeng China 14 329 0.5× 401 1.5× 66 0.8× 18 0.3× 71 1.0× 56 793

Countries citing papers authored by Hwanjun Song

Since Specialization
Citations

This map shows the geographic impact of Hwanjun Song's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Hwanjun Song with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Hwanjun Song more than expected).

Fields of papers citing papers by Hwanjun Song

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Hwanjun Song. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Hwanjun Song. The network helps show where Hwanjun Song may publish in the future.

Co-authorship network of co-authors of Hwanjun Song

This figure shows the co-authorship network connecting the top 25 collaborators of Hwanjun Song. A scholar is included among the top collaborators of Hwanjun Song based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Hwanjun Song. Hwanjun Song is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
2.
3.
Song, Hwanjun, et al.. (2024). Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers With Bridge Block Reconstruction for IoT Systems. IEEE Internet of Things Journal. 11(22). 36384–36396. 3 indexed citations
4.
Song, Hwanjun, et al.. (2024). FineSurE: Fine-grained Summarization Evaluation using LLMs. 906–922. 8 indexed citations
5.
Tang, Liyan, Song Feng, Hwanjun Song, et al.. (2024). TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization. 4455–4480. 8 indexed citations
6.
7.
Song, Hwanjun, Minseok Kim, & Jae-Gil Lee. (2024). Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise. Proceedings of the AAAI Conference on Artificial Intelligence. 38(19). 21592–21601. 7 indexed citations
8.
Kim, Doyoung, et al.. (2024). Adaptive Shortcut Debiasing for Online Continual Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 38(12). 13122–13131. 1 indexed citations
9.
10.
11.
Song, Hwanjun, et al.. (2023). Re-Thinking Federated Active Learning Based on Inter-Class Diversity. 3944–3953. 13 indexed citations
12.
13.
Bang, Jihwan, et al.. (2022). Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9265–9274. 16 indexed citations
14.
Kim, Minseok, et al.. (2022). Meta-Learning for Online Update of Recommender Systems. Proceedings of the AAAI Conference on Artificial Intelligence. 36(4). 4065–4074. 9 indexed citations
15.
Park, Dongmin, Hwanjun Song, Minseok Kim, & Jae-Gil Lee. (2021). Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data. Neural Information Processing Systems. 34. 2 indexed citations
16.
Song, Hwanjun, et al.. (2020). Ada-boundary: accelerating DNN training via adaptive boundary batch selection. Machine Learning. 109(9-10). 1837–1853. 10 indexed citations
17.
Song, Hwanjun, et al.. (2020). Two-Phase Learning for Overcoming Noisy Labels.. 2 indexed citations
18.
Song, Hwanjun, et al.. (2019). Prestopping: How Does Early Stopping Help Generalization Against Label Noise?. arXiv (Cornell University). 8 indexed citations
19.
Song, Hwanjun, Minseok Kim, & Jae-Gil Lee. (2019). SELFIE: Refurbishing Unclean Samples for Robust Deep Learning. International Conference on Machine Learning. 5907–5915. 106 indexed citations
20.
Li, Liang, et al.. (1999). [A study on soil suitability for growth of rhizome of Curcuma longa L].. PubMed. 24(12). 718–21, 763.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Simon Lacoste-Julien Breakdown of academic impact, for papers by Yooju Shin Breakdown of academic impact, for papers by Yilin Yan Breakdown of academic impact, for papers by Xuming Han Breakdown of academic impact, for papers by M. Arif Wani Breakdown of academic impact, for papers by Ilya Loshchilov Breakdown of academic impact, for papers by Xu Jia Breakdown of academic impact, for papers by Shaoning Zeng
Rankless by CCL
2026