🧑‍🔬 Evan Shelhamer

🏛️ Affiliations

🔬Vector InstituteToronto · Canada2025–2026 · 10 papersEmployment since 2025 · Faculty Member and CIFAR AI Chaircurrent🎓University of British ColumbiaVancouver · Canada2025–2026 · 8 papersEmployment since 2025 · Assistant Professor, Computer Sciencecurrent🎓Carleton UniversityOttawa · Canada2025–2026 · 3 paperscurrent🎓University of California, BerkeleyBerkeley · United States2012–2022 · 21 papersEducation 2012–2019 · PhD, Computer Science🏢Google DeepMindLondon · United Kingdom2021–2023 · 5 papersEmployment 2021–2023🏢Adobe SystemsSan Jose · United States2020–2021 · 3 papers

🏛️Google DeepMindSan Francisco · United States2023–2025Employment 2023–2025

🏛️Adobe ResearchCambridge · United States2019–2020Employment 2019–2020

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Caffe: Convolutional Architecture for Fast Feature Embedding (2014 · 4,209 citations)
   Deep convolutional networks had overtaken handcrafted features in visual recognition. Yet reproducing published results often took months, and few toolkits offered fast, ready-to-deploy models. The BVLC team at UC Berkeley presents Caffe, an open-source, BSD-licensed C++ library with CUDA support and Python and…
2. cuDNN: Efficient Primitives for Deep Learning (2014 · 1,240 citations)
   Deep learning frameworks such as Caffe, Theano and Torch7 each maintained hand-tuned GPU kernels for convolution, pooling and activations.

All works

35 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Fully convolutional networks for semantic segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJonathan Long, Evan Shelhamer, Trevor Jackson Darrell2015 · 36,797 citations
2. Fully Convolutional Networks for Semantic Segmentation ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetEvan Shelhamer, Jonathan Long, Trevor Jackson Darrell2016 · 11,507 citations
3. Caffe ↗ACM International Conference on Multimedia (ACM MM) · no summary yetYangqing Jia et al.2014 · 10,940 citations
4. Caffe: Convolutional Architecture for Fast Feature EmbeddingarXiv:1408.5093Yangqing Jia, Evan Shelhamer, Jeff Donahue, et al.2014 · 4,209 citations
5. Deep Layer Aggregation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetFisher Yu et al.2018 · 1,565 citations
6. cuDNN: Efficient Primitives for Deep LearningarXiv 2014 (NVIDIA)Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, et al.2014 · 1,240 citations
7. Tent: Fully Test-time Adaptation by Entropy Minimization ↗arXiv (Cornell University) · no summary yetDequan Wang et al.2020 · 351 citations
8. Perceiver IO: A General Architecture for Structured Inputs & Outputs ↗arXiv (Cornell University) · no summary yetAndrew Jaegle et al.2021 · 283 citations
9. Fully Convolutional Multi-Class Multiple Instance Learning ↗arXiv (Cornell University) · no summary yetDeepak Pathak et al.2014 · 242 citations
10. Clockwork Convnets for Video Semantic Segmentation ↗Lecture notes in computer science · no summary yetEvan Shelhamer et al.2016 · 204 citations
11. Zero-Shot Visual Imitation ↗IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · no summary yetDeepak Pathak et al.2018 · 190 citations
12. Conditional Networks for Few-Shot Semantic Segmentation ↗International Conference on Learning Representations · no summary yetKate Rakelly et al.2018 · 159 citations
13. Few-Shot Segmentation Propagation with Guided Networks ↗arXiv (Cornell University) · no summary yetKate Rakelly et al.2018 · 95 citations
14. Loss is its own Reward: Self-Supervision for Reinforcement Learning ↗arXiv (Cornell University) · no summary yetEvan Shelhamer et al.2016 · 95 citations
15. Back to the Source: Diffusion-Driven Adaptation to Test-Time Corruption ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJin Gao et al.2023 · 72 citations
16. Object Discovery and Representation Networks ↗Lecture notes in computer science · no summary yetOlivier J. Hénaff et al.2022 · 53 citations
17. Scene Intrinsics and Depth from a Single Image ↗no summary yetEvan Shelhamer, Jonathan T. Barron, Trevor Jackson Darrell2015 · 49 citations
18. Fine-grained pose prediction, normalization, and recognition ↗arXiv (Cornell University) · no summary yetNing Zhang et al.2015 · 47 citations
19. Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields ↗arXiv (Cornell University) · no summary yetEvan Shelhamer, Dequan Wang, Trevor Jackson Darrell2019 · 20 citations
20. Back to the Source: Diffusion-Driven Test-Time Adaptation ↗arXiv (Cornell University) · no summary yetJin Gao et al.2022 · 16 citations
21. Exploring Simple and Transferable Recognition-Aware Image Processing ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetZhuang Liu et al.2019 · 14 citations
22. Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks ↗arXiv (Cornell University) · no summary yetDequan Wang et al.2021 · 9 citations
23. Anytime Dense Prediction with Confidence Adaptivity ↗arXiv (Cornell University) · no summary yetZhuang Liu et al.2021 · 8 citations
24. OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation ↗arXiv (Cornell University) · no summary yetHenry Herzog et al.2025 · 4 citations
25. HiP: Hierarchical Perceiver ↗arXiv (Cornell University) · no summary yetJoão Carreira et al.2022 · 4 citations

See all 35 works by Evan Shelhamer →

🤝 Co-authors here

7 co-authors with a page, the most papers together first.

• Bryan Catanzaro
• Jeff Donahue
• Jonathan Cohen
• Ross Girshick
• Sergio Guadarrama
• Trevor Jackson Darrell
• Yangqing Jia

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×3
• IEEE Transactions on Pattern Analysis and Machine Intelligence ×3
• International Conference on Learning Representations ×2
• Lecture notes in computer science ×2
• ACM International Conference on Multimedia (ACM MM)
• IEEE Geoscience and Remote Sensing Magazine
• IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

🔗 Cited by

Papers of our library cite their works 1,602 times (of the 149,439 papers whose bibliographies we read); 75 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/evan-shelhamer/