I am an Assistant Professor in the
Department of Computer Science
at the
University of Chicago.
I have a courtesy appointment at the
Toyota Technological Institute at Chicago (TTIC).
Previously, I was a Research Assistant Professor at
TTIC,
following a time as a postdoc in the
Computer Vision Lab at
Caltech.
I completed my Ph.D. at
UC Berkeley, advised by
Jitendra Malik.
Contact
The University of Chicago
Department of Computer Science
John Crerar Library Building
5730 S. Ellis Ave
Chicago, IL 60637
mmaire@uchicago.edu
Department of Computer Science
John Crerar Library Building
5730 S. Ellis Ave
Chicago, IL 60637
mmaire@uchicago.edu
Students
- Xin Yuan (University of Chicago)
- Xiao Zhang (University of Chicago)
- Sudarshan Babu (TTIC)
- Pedro Savarese (TTIC)
-
Tri Huynh
(University of Chicago), Ph.D., 2021 → Google
Thesis: Universal Neural Memory Architectures: Multigrid Connectivity, Domain-Agnostic Geometry, and Local Operators
Publications
All|
Selected|
|
Information-Theoretic Segmentation by Inpainting Error Maximization
Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, and David McAllesterComputer Vision and Pattern Recognition (CVPR), 2021
An optimization approach to unsupervised image segmentation that minimizes predictability of foreground
from background and vice-versa, optionally producing pseudo-labels for training deep models.
Abstract
Domain-Independent Dominance of Adaptive Methods
Pedro Savarese, David McAllester, Sudarshan Babu, and Michael MaireComputer Vision and Pattern Recognition (CVPR), 2021
AvaGrad: an adaptive optimizer that matches or outperforms both Adam and SGD, simplifies
hyperparameter tuning by decoupling learning rate from adaptivity, and improves training of GANs.
Abstract
Multimodal Contrastive Training for Visual Representation Learning
Xin Yuan, Zhe Lin, Jason Kuen, Jianming Zhang, Yilin Wang, Michael Maire, Ajinkya Kale, and Baldo FaietaComputer Vision and Pattern Recognition (CVPR), 2021
A self-supervised learning framework connecting vision and language in a common embedding space,
with both inter-modal and intra-modal contrastive objectives.
Abstract
Are Machine Learning Cloud APIs Used Correctly?
Chengcheng Wan, Shicheng Liu, Henry Hoffmann, Michael Maire, and Shan LuInternational Conference on Software Engineering (ICSE), 2021
An analysis of open-source applications that use cloud-based machine learning APIs, in combination with
development of automated checkers for identifying API misuses.
Abstract
Growing Efficient Deep Networks by Structured Continuous Sparsification
Xin Yuan, Pedro Savarese, and Michael MaireInternational Conference on Learning Representations (ICLR), 2021 [Oral]
Accelerated training of compact neural networks by growing them from a small seed architecture, using
a combination of continuous sparsification with a sampling scheme; unifies pruning and architecture
search.
Abstract
Winning the Lottery with Continuous Sparsification
Pedro Savarese*, Hugo Silva*, and Michael MaireNeural Information Processing Systems (NeurIPS), 2020
A singular approach to pruning neural networks and finding lottery tickets (sparse subnetworks,
retrainable from initialization), with experimental results setting a new state-of-the-art for each.
Abstract
Self-Supervised Visual Representation Learning from Hierarchical Grouping
Xiao Zhang and Michael MaireNeural Information Processing Systems (NeurIPS), 2020 [Spotlight]
A generic image segmentation procedure, trained on small dataset, bootstraps self-supervised
representation learning on a large unlabeled dataset using a region-aware contrastive loss.
Abstract
Multigrid Neural Memory
Tri Huynh, Michael Maire, and Matthew R. WalterInternational Conference on Machine Learning (ICML), 2020
A design for endowing neural networks with hierarchically-connected distributed memory; end-to-end
training yields the emergence of coherent memory subsystems driven by learned addressing strategies.
Abstract
Orthogonalized SGD and Nested Architectures for Anytime Neural Networks
Chengcheng Wan, Henry Hoffmann, Shan Lu, and Michael MaireInternational Conference on Machine Learning (ICML), 2020
The principle of maximizing re-use of intermediate representations within a multitask network guides
design of multistage nested network architectures paired with a custom training procedure.
Abstract
ALERT: Accurate Anytime Learning for Energy and Timeliness
Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, and Shan LuUSENIX Annual Technical Conference (USENIX ATC), 2020
A runtime scheduler for selecting neural network and system resource configurations to meet latency,
accuracy, and energy constraints in dynamic operating environments.
Abstract
Pixel Consensus Voting for Panoptic Segmentation
Haochen Wang, Ruotian Luo, Michael Maire, and Greg ShakhnarovichComputer Vision and Pattern Recognition (CVPR), 2020
Object segmentation based on the generalized Hough transform, which accumulates pixelwise votes for
instance centroids over discrete spatial cells, implemented within a deep convolutional framework.
Abstract
Learning Implicitly Recurrent CNNs Through Parameter Sharing
Pedro Savarese and Michael MaireInternational Conference on Learning Representations (ICLR), 2019
Re-parameterizing convolutional networks, so that layers share weights via a set of templates, benefits
generalization and often produces trained models that can be rewritten in an explicitly recurrent form.
Abstract
Sparsely Aggregated Convolutional Networks
Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, and Ping TanEuropean Conference on Computer Vision (ECCV), 2018
Scaling skip or residual connection scaffolding logarithmically, rather than linearly (standard ResNet),
with network depth increases parameter efficiency and permits training models thousands of layers deep.
Abstract
Self-Supervised Relative Depth Learning for Urban Scene Understanding
Huaizu Jiang, Erik Learned-Miller, Gustav Larsson, Michael Maire, and Greg ShakhnarovichEuropean Conference on Computer Vision (ECCV), 2018
Predicting relative depth from a single source image serves as proxy task for self-supervised
learning; trained from egomotion video, these learned representations boost several downstream tasks.
Abstract
Regularizing Deep Networks by Modeling and Predicting Label Structure
Mohammadreza Mostajabi, Michael Maire, and Gregory ShakhnarovichComputer Vision and Pattern Recognition (CVPR), 2018
Learning an autoencoder for a structured label space (e.g., semantic segmentation annotations),
allows subsequent use of its decoder as an auxiliary output branch to regularize training of a
prediction network.
Abstract
Colorization as a Proxy Task for Visual Understanding
Gustav Larsson, Michael Maire, and Gregory ShakhnarovichComputer Vision and Pattern Recognition (CVPR), 2017
Requiring no labeled data, colorizing images serves as an effective training proxy for downstream
classification and semantic segmentation tasks; we quantify in comparison to ImageNet pretraining.
Abstract
Multigrid Neural Architectures
Tsung-Wei Ke, Michael Maire, and Stella X. YuComputer Vision and Pattern Recognition (CVPR), 2017
Endowing CNNs with spatial shortcuts, by remaking layers into multigrid pyramids with bidirectional
wiring across grid scales, yields an emergent capability: attentional behavior arises from end-to-end
training.
Abstract
FractalNet: Ultra-Deep Neural Networks without Residuals
Gustav Larsson, Michael Maire, and Gregory ShakhnarovichInternational Conference on Learning Representations (ICLR), 2017
A self-similar architecture shows that shortcut pathways across depth, not the functional form of
residual connections, are key to training networks, allowing them to transition from effectively
shallow to deep.
Abstract
Learning Representations for Automatic Colorization
Gustav Larsson, Michael Maire, and Gregory ShakhnarovichEuropean Conference on Computer Vision (ECCV), 2016 [Oral]
A hypercolumn architecture and a loss formulated on histogram prediction serve as the basis for training
a colorization network that outperforms existing methods and yields broadly useful feature
representations.
Abstract
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
Michael Maire, Takuya Narihira, and Stella X. YuComputer Vision and Pattern Recognition (CVPR), 2016 [Spotlight]
Spectral embedding resolves predictions, produced by a CNN, about local figure/ground and grouping
relationships into a globally consistent segmentation and figure/ground organization of a scene.
Abstract
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
Takuya Narihira, Michael Maire, and Stella X. YuInternational Conference on Computer Vision (ICCV), 2015
Trained on the synthetic MPI Sintel dataset to directly predict albedo and shading channels from an
input RGB image, a convolutional neural network generalizes well to producing decompositions of real
images.
Abstract
Learning Lightness from Human Judgement on Relative Reflectance
Takuya Narihira, Michael Maire, and Stella X. YuComputer Vision and Pattern Recognition (CVPR), 2015
An approach to predicting relative lightness (perceived reflectance) of image patches using deep
features, with promising results on the Intrinsic Images in the Wild dataset.
Abstract
Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling
Michael Maire, Stella X. Yu, and Pietro PeronaAsian Conference on Computer Vision (ACCV), 2014 [Oral]
Deep, multiscale feature representations based on sparse coding; articulates the concept of
concatenating a spatially-localized slice through multiple layers of sparse codes (activations) into a
feature descriptor.
Abstract
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence ZitnickEuropean Conference on Computer Vision (ECCV), 2014 [Oral]
A large-scale dataset for object detection and segmentation.
Abstract
Progressive Multigrid Eigensolvers for Multiscale Spectral Segmentation
Michael Maire and Stella X. YuInternational Conference on Computer Vision (ICCV), 2013
A custom eigensolver, using a novel interpolation strategy, for spectral clustering problems with
coarse-to-fine structure and (optional) constraints; applied to image segmentation, it delivers a
substantial speedup.
Abstract
Hierarchical Scene Annotation
Michael Maire, Stella X. Yu, and Pietro PeronaBritish Machine Vision Conference (BMVC), 2013
Web-based software tools for detailed annotation of scenes into object-part-subpart region hierarchies
and their occlusion relationships.
Abstract
Object Detection and Segmentation from Joint Embedding of Parts and Pixels
Michael Maire, Stella X. Yu, and Pietro PeronaInternational Conference on Computer Vision (ICCV), 2011 [Oral]
A model of pixel grouping, part grouping, and figure/ground relationships as interactions between
graph nodes, with a globally consistent scene interpretation obtained by solving an Angular Embedding
problem.
Abstract
Occlusion Boundary Detection and Figure/Ground Assignment from Optical Flow
Patrik Sundberg, Thomas Brox, Michael Maire, Pablo Arbeláez, and Jitendra MalikComputer Vision and Pattern Recognition (CVPR), 2011 [Oral]
A contour detection procedure for video that exploits motion cues and, in combination with reasoning
about optical flow over a segmentation into regions, determines figure/ground relationships.
Abstract
Contour Detection and Hierarchical Image Segmentation
Pablo Arbeláez, Michael Maire, Charless Fowlkes, and Jitendra MalikIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2011
A high-performance contour detector, combining local and global information, and generic machinery for
transforming contours into a hierarchical region tree; extensive quantitative evaluation.
Abstract
Simultaneous Segmentation and Figure/Ground Organization using Angular Embedding
Michael MaireEuropean Conference on Computer Vision (ECCV), 2010
Angular Embedding, an extension of spectral clustering to complex-valued affinities, provides the
basis for incorporating figure/ground ordering relationships into an image segmentation framework.
Abstract
From Contours to Regions: An Empirical Evaluation
Pablo Arbeláez, Michael Maire, Charless Fowlkes, and Jitendra MalikComputer Vision and Pattern Recognition (CVPR), 2009
An Oriented variant of the Watershed Transform (OWT), followed by construction of an Ultrametic Contour
Map (UCM), together serve to convert contours into a region hierarchy, while preserving boundary quality.
Abstract
Using Contours to Detect and Localize Junctions in Natural Images
Michael Maire, Pablo Arbeláez, Charless Fowlkes, and Jitendra MalikComputer Vision and Pattern Recognition (CVPR), 2008 [Oral]
A method for enhancing local contour detection with global information obtained from spectral
partitioning, and a novel iterative approach to localizing junctions from contour fragments.
Abstract
SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition
Hao Zhang, Alexander C. Berg, Michael Maire, and Jitendra MalikComputer Vision and Pattern Recognition (CVPR), 2006
A hybridization of support vector machines (SVMs) and nearest neighbor classification, achieved by
training a local SVM on the collection of neighbors close to a query point.
Abstract
Making Latin Manuscripts Searchable using gHMM's
Jaety Edwards, Yee Whye Teh, David A. Forsyth, Roger Bock, Michael Maire, and Grace VesomNeural Information Processing Systems (NeurIPS), 2004
A system for making scanned, handwritten latin manuscripts accessible to full text search, while
requiring only a small amount of annotated training data.
Abstract
Names and Faces in the News
Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee Whye Teh, Erik Learned-Miller, and David A. ForsythComputer Vision and Pattern Recognition (CVPR), 2004
A large dataset of faces obtained from captioned news images.
Abstract
Recognition by Probabilistic Hypothesis Construction
Pierre Moreels, Michael Maire, and Pietro PeronaEuropean Conference on Computer Vision (ECCV), 2004
A probabilistic framework for recognizing individual object instances in images of cluttered scenes.
Abstract
Theses
Contour Detection and Image Segmentation
Michael MairePh.D. Thesis
University of California, Berkeley, 2009
Abstract
Dynamic Code Updates
Michael MaireUndergraduate Thesis
California Institute of Technology, 2003
Abstract
Copyright © 2021 Michael Maire