ES
Evan Shelhamer
cs.CVcs.LGstat.MLcs.AIcs.CRcs.NEArtificial Intelligence and Roboticscs.CLcs.CYcs.MS
On Valency
published · living versionsW_kmjwgbm3·v1 · currentpublished
Caffe: Convolutional Architecture for Fast Feature Embedding
with Yangqing Jia, Jeff Donahue, Sergey Karayev, Jonathan Long +3
1 version
Preprints & journals
44 papers in the corpus · 2014–2026MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale2609.25454v2 · Isaac Corley, Arjun Rao, Esther Rolf et al.2026 · 0 citationsarXiv
No One Knows the State of the Art in Geospatial Foundation Models2605.12678v3 · Isaac Corley, Nils Lehmann, Caleb Robinson et al.2026 · 1 citationarXiv
LookThere! Sparse Vision by Reinforced Selection2609.04698v1 · Sreehari Rammohan, Yousef Yassin, Anthony Fuller et al.2026 · 0 citationsarXiv
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning2603.15553v2 · Scott C. Lowe, Anthony Fuller, Sageev Oore et al.2026 · 0 citationsarXiv
Private and Stable Test-Time Adaptation with Differential Privacy2606.01908v2 · Zefeng Li, Qiaoyue Tang, Mathias Lecuyer et al.2026 · 0 citationsarXiv
Changing Modalities: Adapting Remote Sensing Models to New Satellites and Sensors2606.23356v1 · Tim G. Zhou, Anthony Fuller, Geoff Pleiss et al.2026 · 0 citationsarXiv
Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark2606.23615v1 · Nathan Senyard, Salem Hamdani, Astrid Zhang et al.2026 · 0 citationsarXiv
Self-Soupervision: Cooking Model Soups without Labels2602.02890v2 · Anthony Fuller, James R. Green, Evan Shelhamer2026 · 0 citationsarXiv
A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation2606.01973v1 · Zefeng Li, Evan Shelhamer2026 · 0 citationsarXiv
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute2605.06809v1 · Ali Salamatian, Anthony Fuller, Pritam Sarkar et al.2026 · 0 citationsarXiv
ProtoTTA: Prototype-Guided Test-Time Adaptation2604.15494v1 · Mohammad Mahdi Abootorabi, Parvin Mousavi, Purang Abolmaesumi et al.2026 · 0 citationsarXiv
Earth Embeddings: Towards AI-centric Representations of our Planetx5hx9s · Konstantin Klemmer, Esther Rolf, Marc Russwurm et al.2025 · 3 citationsEarthArXiv
OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation2511.13655v1 · Henry Herzog, Favyen Bastani, Yawen Zhang et al.2025 · 1 citationarXiv
ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains2505.14511v3 · Guillaume Vray, Devavrat Tomar, Xufeng Gao et al.2025 · 2 citationsarXiv
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences2406.10427v3 · Saiyue Lyu, Shadab Shaikh, Frederick Shpilevskiy et al.2024 · 0 citationsarXiv
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities2502.09356v3 · Gabriel Tseng, Anthony Fuller, Marlena Reil et al.2025 · 1 citationarXiv
Back to the Source: Diffusion-Driven Test-Time Adaptation2207.03442v2 · Jin Gao, Jialing Zhang, Xihui Liu et al.2022 · 14 citationsarXiv
Exploring Simple and Transferable Recognition-Aware Image Processing.35704542 · Liu, Zhuang, Wang, Hungju, Zhou, Tinghui et al.2023 · 14 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(3):3032-3046
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts2302.10164v1 · Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer et al.2023 · 11 citationsarXiv
HiP: Hierarchical Perceiver2202.10890v2 · Joao Carreira, Skanda Koppula, Daniel Zoran et al.2022 · 3 citationsarXiv
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods2209.15589v4 · Skanda Koppula, Yazhe Li, Evan Shelhamer et al.2022 · 4 citationsarXiv
Exploring Simple and Transferable Recognition-Aware Image Processing1910.09185v4 · Zhuang Liu, Hung-Ju Wang, Tinghui Zhou et al.2019 · 14 citationsarXiv
Object discovery and representation networks2203.08777v3 · Olivier J. H'enaff, Skanda Koppula, Evan Shelhamer et al.2022 · 50 citationsarXiv
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses2202.13711v2 · Francesco Croce, Sven Gowal, Thomas Brunner et al.2022 · 10 citationsarXiv
Anytime Dense Prediction with Confidence Adaptivity2104.00749v2 · Zhuang Liu, Zhiqiu Xu, Hung-Ju Wang et al.2021 · 4 citationsarXiv
Perceiver IO: A General Architecture for Structured Inputs & Outputs2107.14795v3 · Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.2021 · 226 citationsarXiv
On-target Adaptation2109.01087v1 · Dequan Wang, Shaoteng Liu, Sayna Ebrahimi et al.2021 · 0 citationsarXiv
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks2105.08714v1 · Dequan Wang, An Ju, Evan Shelhamer et al.2021 · 8 citationsarXiv
Tent: Fully Test-time Adaptation by Entropy Minimization2006.10726v3 · Dequan Wang, Evan Shelhamer, Shaoteng Liu et al.2020 · 286 citationsarXiv
It Is Likely That Your Loss Should be a Likelihood2007.06059v2 · Mark Hamilton, Evan Shelhamer, William T. Freeman2020 · 2 citationsarXiv
Dynamic Scale Inference by Entropy Minimization1908.03182v1 · Dequan Wang, Evan Shelhamer, Bruno Olshausen et al.2019 · 5 citationsarXiv
Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields1904.11487v1 · Evan Shelhamer, Dequan Wang, Trevor Darrell2019 · 27 citationsarXiv
Infinite Mixture Prototypes for Few-Shot Learning1902.04552v1 · Kelsey R. Allen, Evan Shelhamer, Hanul Shin et al.2019 · 79 citationsarXiv
Deep Layer Aggregation1707.06484v3 · Fisher Yu, Dequan Wang, Evan Shelhamer et al.2017 · 33 citationsarXiv
Fully Convolutional Networks for Semantic Segmentation.27244717 · Shelhamer, Evan, Long, Jonathan, Darrell, Trevor2018 · 14,536 citationsIEEE transactions on pattern analysis and machine intelligence. 2017;39(4):640-651
Few-Shot Segmentation Propagation with Guided Networks1806.07373v1 · Kate Rakelly, Evan Shelhamer, Trevor Darrell et al.2018 · 100 citationsarXiv
Zero-Shot Visual Imitation1804.08606v1 · Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo et al.2018 · 196 citationsarXiv
Loss is its own Reward: Self-Supervision for Reinforcement Learning1612.07307v2 · Evan Shelhamer, Parsa Mahmoudieh, Max Argus et al.2016 · 85 citationsarXiv
Clockwork Convnets for Video Semantic Segmentation1608.03609v1 · Evan Shelhamer, Kate Rakelly, Judy Hoffman et al.2016 · 210 citationsarXiv
Fully Convolutional Networks for Semantic Segmentation1605.06211v1 · Evan Shelhamer, Jonathan Long, Trevor Darrell2016 · 38,580 citationsarXivon Valency
Fine-grained pose prediction, normalization, and recognition1511.07063v1 · Ning Zhang, Evan Shelhamer, Yang Gao et al.2015 · 50 citationsarXiv
Fully Convolutional Networks for Semantic Segmentation1411.4038v2 · Jonathan Long, Evan Shelhamer, Trevor Darrell2014 · 38,910 citationsarXiv
cuDNN: Efficient Primitives for Deep Learning1410.0759v3 · Sharan Chetlur, Cliff Woolley, Philippe Vandermersch et al.2014 · 1,025 citationsarXivon Valency
Caffe: Convolutional Architecture for Fast Feature Embedding1408.5093v1 · Yangqing Jia, Evan Shelhamer, Jeff Donahue et al.2014 · 4,261 citationsarXivon Valency
Career total: 64 works. 44 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.