Abhijit Guha Roy

Artificial Intelligence · 2017–2025

A researcher in the Science corpus: 9 papers; trusts 209 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 90 citations into it; #14,970 of 35,345 by trust here, #10,207 by citations
• Computer Vision and Pattern Recognition — 85 citations into it; #9,736 of 21,575 by trust here, #10,010 by citations
• Safety, Robustness & Interpretability — 20 citations into it
• Optimization & Training — 19 citations into it
• Model Architectures — 17 citations into it; #1,595 of 2,278 by trust here, #1,774 by citations
• Meta & Continual Learning — 8 citations into it
• Media Technology — 6 citations into it
• Biophysics — 5 citations into it

Whom Abhijit Guha Roy trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Kaiming He
4. Olaf Ronneberger
5. Ilya Sutskever
6. Hyeonwoo Noh
7. Yoshua Bengio
8. Diederik P. Kingma
9. Yann LeCun
10. Evan Shelhamer

Who trusts Abhijit Guha Roy overall

1. Valerio Marsocci
2. Yauhen Babakhin
3. Tongwen Huang
4. Zequn Qin
5. Nassir Navab
6. Qingyan Bai
7. Qilong Wang
8. Zhiyi Tian
9. Rodolfo Stoffel Antunes
10. Meng-Hao Guo

Papers from Abhijit Guha Roy's perspective

Ordered by how strongly the researchers Abhijit Guha Roy 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. Gradient-based learning applied to document recognition
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness (2019) — 22 citations
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection (2021) — 310 citations
• Contrastive Training for Improved Out-of-Distribution Detection (2020) — 271 citations
• ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network (2017) — 577 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Importance Driven Continual Learning for Segmentation Across Domains (2020) — 36 citations
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning (2019) — 359 citations
• Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks (2018) — 1,025 citations
• Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks (2018) — 467 citations