Byeongho Heo

2.7k citations
26 papers · 1.3k · 2 hit papers · h-index 13

Impact in

    • Advanced Neural Network Applications
    • Advanced Image and Video Retrieval Techniques
    • Video Surveillance and Tracking Methods
    • Multimodal Machine Learning Applications
    • Domain Adaptation and Few-Shot Learning
    • Adversarial Robustness in Machine Learning
    • Machine Learning and Data Classification
    • Anomaly Detection Techniques and Applications

Papers in

    • Advanced Neural Network Applications 12
    • Advanced Image and Video Retrieval Techniques 10
    • Video Surveillance and Tracking Methods 5
    • Multimodal Machine Learning Applications 4
    • Advanced Vision and Imaging 3
    • Domain Adaptation and Few-Shot Learning 13
    • Adversarial Robustness in Machine Learning 3
    • Anomaly Detection Techniques and Applications 3

Byeongho Heo

25 papers receiving 1.3k citations

Byeongho Heo's Hit Papers

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons 2019 · 291 citations
2910+2+4Years since publication100200300

Peers

Byeongho Heo
Comparison fields: 5 of 94
  • Computer Vision and Pattern Recognition 830
  • Artificial Intelligence 701
  • Signal Processing 76
  • Media Technology 62
  • Computational Mathematics 4
Replace Donggyu Joo with:
Donggyu Joo South Korea
Junho Yim South Korea
Zixing Song Hong Kong
Alaaeldin El-Nouby Sweden
Keze Wang China
Xiushan Nie China
Arun Mallya United States
Chunfeng Yuan China
Byeongho Heo relative to Donggyu Joo South Korea Donggyu Joo's profile →
Citations per field
00.5×1.5×2.5×
Donggyu Joo · 1×
Citations per year

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-authors

The 25 scholars most cited alongside Byeongho Heo, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Byeongho Heo Line = papers co-authored together Byeongho Heo links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 26 papers — load more, or switch the sort, to bring in the rest.

#Work
1
A Comprehensive Overhaul of Feature Distillation
Hit paper breakdown →
2019375
2
Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
Hit paper breakdown →
2019291
3 2022122
4 2021101
5 201982
6 202264
7 202160
8 202150
9 202321
10 201919
11 201719
12
ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network.
202017
13 201313
14
Slowing Down the Weight Norm Increase in Momentum-based Optimizers
20209
15 20218
16
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
20217
17 20186
18 20206
19
Improving Knowledge Distillation with Supporting Adversarial Samples
20184
20 20213

About Byeongho Heo

Byeongho Heo is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Aerospace Engineering, Electrical and Electronic Engineering and Computer Graphics and Computer-Aided Design, having authored 26 papers that have together received 1.3k indexed citations. Recurring topics across this work include Domain Adaptation and Few-Shot Learning (13 papers), Advanced Neural Network Applications (12 papers), Advanced Image and Video Retrieval Techniques (10 papers), Video Surveillance and Tracking Methods (5 papers), Multimodal Machine Learning Applications (4 papers), Adversarial Robustness in Machine Learning (3 papers), Anomaly Detection Techniques and Applications (3 papers) and Advanced Vision and Imaging (3 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (830 citations), Artificial Intelligence (701 citations), Signal Processing (76 citations), Media Technology (62 citations) and Computational Mathematics (4 citations). Byeongho Heo has collaborated with scholars based in South Korea, United Kingdom and Canada. Frequent co-authors include Sangdoo Yun, Jin Young Choi, Minsik Lee, Hyojin Park, Jeesoo Kim, Nojun Kwak, Mingi Ji, Dongyoon Han, Seulki Park and Jong‐Seok Lee. Their work appears in journals such as IEEE Access, Pattern Recognition Letters, IEEE Transactions on Neural Networks and Learning Systems, Machine Vision and Applications and Seoul National University Open Repository (Seoul National University).

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