Byeongho Heo

2.6k total citations · 2 hit papers
26 papers, 1.2k citations indexed

About

Byeongho Heo is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Aerospace Engineering. According to data from OpenAlex, Byeongho Heo has authored 26 papers receiving a total of 1.2k indexed citations (citations by other indexed papers that have themselves been cited), including 23 papers in Computer Vision and Pattern Recognition, 15 papers in Artificial Intelligence and 1 paper in Aerospace Engineering. Recurrent topics in Byeongho Heo's work include Domain Adaptation and Few-Shot Learning (13 papers), Advanced Neural Network Applications (12 papers) and Advanced Image and Video Retrieval Techniques (10 papers). Byeongho Heo is often cited by papers focused on Domain Adaptation and Few-Shot Learning (13 papers), Advanced Neural Network Applications (12 papers) and Advanced Image and Video Retrieval Techniques (10 papers). Byeongho Heo collaborates with scholars based in South Korea, United Kingdom and Canada. Byeongho Heo's co-authors include Sangdoo Yun, Jin Young Choi, Minsik Lee, Jeesoo Kim, Nojun Kwak, Hyojin Park, Dongyoon Han, Mingi Ji, Seulki Park and Jong‐Seok Lee and has published in prestigious journals such as IEEE Access, IEEE Transactions on Neural Networks and Learning Systems and Pattern Recognition Letters.

In The Last Decade

Byeongho Heo

25 papers receiving 1.2k citations

Hit Papers

A Comprehensive Overhaul of Feature Distillation 2019 2026 2021 2023 2019 2019 100 200 300
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. A Comprehensive Overhaul of Feature Distillation
    2019 357 citations Byeongho Heo, Sangdoo Yun et al. profile →
  2. Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
    2019 276 citations Byeongho Heo, Minsik Lee et al. Proceedings of the AAAI Conference on Artificial Intelligence profile →

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Byeongho Heo South Korea 13 809 678 73 70 61 26 1.2k
Donggyu Joo South Korea 7 757 0.9× 641 0.9× 57 0.8× 56 0.8× 83 1.4× 11 1.2k
Xiaoshan Yang China 21 969 1.2× 553 0.8× 65 0.9× 52 0.7× 95 1.6× 84 1.4k
Alaaeldin El-Nouby Sweden 4 438 0.5× 352 0.5× 75 1.0× 79 1.1× 52 0.9× 6 835
Keze Wang China 16 874 1.1× 543 0.8× 46 0.6× 75 1.1× 110 1.8× 38 1.3k
Nicolas Thome France 17 860 1.1× 574 0.8× 67 0.9× 40 0.6× 141 2.3× 43 1.3k
Arun Mallya United States 13 1.2k 1.4× 716 1.1× 127 1.7× 59 0.8× 66 1.1× 16 1.7k
Donghyun Kim South Korea 15 508 0.6× 591 0.9× 60 0.8× 64 0.9× 45 0.7× 59 998
Han-Jia Ye China 19 778 1.0× 1.2k 1.8× 91 1.2× 164 2.3× 83 1.4× 57 1.6k
Bo Xiong United States 15 980 1.2× 412 0.6× 76 1.0× 31 0.4× 55 0.9× 23 1.3k

Countries citing papers authored by Byeongho Heo

Since Specialization
Citations

This map shows the geographic impact of Byeongho Heo'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 Byeongho Heo with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Byeongho Heo more than expected).

Fields of papers citing papers by Byeongho Heo

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Byeongho Heo. 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 Byeongho Heo. The network helps show where Byeongho Heo may publish in the future.

Co-authorship network of co-authors of Byeongho Heo

This figure shows the co-authorship network connecting the top 25 collaborators of Byeongho Heo. A scholar is included among the top collaborators of Byeongho Heo 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 Byeongho Heo. Byeongho Heo 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.
Kang, Junyong, Byeongho Heo, & Junsuk Choe. (2024). Improving ViT interpretability with patch-level mask prediction. Pattern Recognition Letters. 187. 73–79.
2.
Chun, Sanghyuk, et al.. (2023). SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage. 17202–17213. 3 indexed citations
3.
Heo, Byeongho, et al.. (2023). Scratching Visual Transformer's Back with Uniform Attention. 5784–5795. 20 indexed citations
4.
Heo, Byeongho, et al.. (2022). Joint Global and Local Hierarchical Priors for Learned Image Compression. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5982–5991. 60 indexed citations
5.
Heo, Byeongho, Sanghyuk Chun, Seong Joon Oh, et al.. (2021). AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights. International Conference on Learning Representations. 7 indexed citations
6.
Ji, Mingi, et al.. (2021). Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching. Proceedings of the AAAI Conference on Artificial Intelligence. 35(9). 7945–7952. 93 indexed citations
7.
Heo, Byeongho, Sangdoo Yun, Dongyoon Han, et al.. (2021). Rethinking Spatial Dimensions of Vision Transformers. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 11916–11925. 2 indexed citations
8.
Yun, Sangdoo, et al.. (2021). Detecting and Removing Text in the Wild. IEEE Access. 9. 123313–123323. 2 indexed citations
9.
Chang, Hyung Jin, et al.. (2021). Motion-aware ensemble of three-mode trackers for unmanned aerial vehicles. Machine Vision and Applications. 32(3). 2 indexed citations
10.
Choi, Jongwon, et al.. (2021). Rollback Ensemble With Multiple Local Minima in Fine-Tuning Deep Learning Networks. IEEE Transactions on Neural Networks and Learning Systems. 33(9). 4648–4660. 7 indexed citations
11.
Heo, Byeongho, Sanghyuk Chun, Seong Joon Oh, et al.. (2020). Slowing Down the Weight Norm Increase in Momentum-based Optimizers. arXiv (Cornell University). 9 indexed citations
12.
Han, Dongyoon, Sangdoo Yun, Byeongho Heo, & Young Joon Yoo. (2020). ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network.. arXiv (Cornell University). 16 indexed citations
13.
Heo, Byeongho, Minsik Lee, Sangdoo Yun, & Jin Young Choi. (2019). Knowledge Distillation with Adversarial Samples Supporting Decision Boundary. Proceedings of the AAAI Conference on Artificial Intelligence. 33(1). 3771–3778. 80 indexed citations
14.
Heo, Byeongho, Minsik Lee, Sangdoo Yun, & Jin Young Choi. (2019). Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons. Proceedings of the AAAI Conference on Artificial Intelligence. 33(1). 3779–3787. 276 indexed citations breakdown →
15.
Heo, Byeongho, Minsik Lee, Sangdoo Yun, & Jin Young Choi. (2018). Improving Knowledge Distillation with Supporting Adversarial Samples. arXiv (Cornell University). 3 indexed citations
16.
Yoo, Youngjoon, et al.. (2018). Pose transforming network: Learning to disentangle human posture in variational auto-encoded latent space. Pattern Recognition Letters. 112. 91–97. 6 indexed citations
17.
Heo, Byeongho, et al.. (2017). Deep learning architecture for pedestrian 3-D localization and tracking using multiple cameras. 1147–1151. 1 indexed citations
18.
Heo, Byeongho, Kimin Yun, & Jin Young Choi. (2017). Appearance and motion based deep learning architecture for moving object detection in moving camera. 1827–1831. 19 indexed citations
19.
Yun, Sangdoo, et al.. (2014). Self-Organizing Cascaded Structure of Deformable Part Models for Fast Object Detection. 20. 4246–4250. 1 indexed citations
20.
Yi, Kwang Moo, et al.. (2013). Initialization-Insensitive Visual Tracking through Voting with Salient Local Features. University of Birmingham Research Portal (University of Birmingham). 2912–2919. 13 indexed citations

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 Donggyu Joo Breakdown of academic impact, for papers by Xiaoshan Yang Breakdown of academic impact, for papers by Alaaeldin El-Nouby Breakdown of academic impact, for papers by Keze Wang Breakdown of academic impact, for papers by Nicolas Thome Breakdown of academic impact, for papers by Arun Mallya Breakdown of academic impact, for papers by Donghyun Kim Breakdown of academic impact, for papers by Han-Jia Ye Breakdown of academic impact, for papers by Bo Xiong
Rankless by CCL
2026