Ser-Nam Lim

Computer Vision and Pattern Recognition · 2017–2023

A researcher in the Science corpus: 24 papers; trusts 1,969 researchers and is trusted by 60 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 770 citations into it; #4,085 of 21,575 by trust here, #2,410 by citations
• Artificial Intelligence — 653 citations into it; #11,001 of 35,345 by trust here, #4,298 by citations
• Representation & Self-Supervised Learning — 182 citations into it
• Model Architectures — 164 citations into it
• Optimization & Training — 86 citations into it
• Evaluation & Benchmarks — 85 citations into it
• Safety, Robustness & Interpretability — 70 citations into it; #1,958 of 2,251 by trust here, #1,780 by citations
• Efficiency & Compression — 62 citations into it

Whom Ser-Nam Lim trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Diederik P. Kingma
5. Yoshua Bengio
6. Ross B. Girshick
7. Yann LeCun
8. Ilya Sutskever
9. Karen Simonyan
10. Christian Szegedy

Who trusts Ser-Nam Lim overall

1. Da-Wei Zhou
2. Marco Toldo
3. Sungmin Cha
4. Serban Stan
5. Kuniaki Saito

Papers from Ser-Nam Lim's perspective

Ordered by how strongly the researchers Ser-Nam Lim trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation (2017) — 527 citations
• A Metric Learning Reality Check (2020) — 537 citations
• SS-IL: Separated Softmax for Incremental Learning (2020) — 219 citations
• Visual Prompt Tuning (2022) — 2,722 citations
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation (2018) — 273 citations
• On Feature Normalization and Data Augmentation (2020) — 164 citations
• Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning (2022) — 144 citations
• What makes fake images detectable? Understanding properties that generalize (2020) — 454 citations
• Enhancing Adversarial Example Transferability With an Intermediate Level Attack (2019) — 300 citations
• Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors (2019) — 325 citations
• Exploring Visual Engagement Signals for Representation Learning (2021) — 15 citations
• HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions (2022) — 401 citations
• Measuring Dataset Granularity (2019) — 14 citations
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (2020) — 328 citations
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods (2021) — 492 citations
• Regularizing deep networks using efficient layerwise adversarial training (2017) — 103 citations
• Adaptive RNN Tree for Large-Scale Human Action Recognition (2017) — 104 citations
• Differentiating through the Fréchet Mean (2020) — 87 citations
• Metric Compatible Training for Online Backfilling in Large-Scale Retrieval (2023) — 9 citations
• Computationally Budgeted Continual Learning: What Does Matter? (2023) — 90 citations