622 citations · 948 across the 19 of their papers we have counts for
24 papers
Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
Xin Yuan, Pedro Savarese, Michael Maire
We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dyna…
Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits
Zhuokai Zhao, Takumi Matsuzawa, William Irvine +2
Proper evaluations are crucial for better understanding, troubleshooting, interpreting model behaviors and further improving model performance. While using scalar-based error metri…
Multimodal Contrastive Training for Visual Representation Learning
Xin Yuan, Zhe Lin, Jason Kuen +5
We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlik…
Self-Supervised Visual Representation Learning from Hierarchical Grouping
Xiao Zhang, Michael Maire
We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partition…
Information-Theoretic Segmentation by Inpainting Error Maximization
Pedro Savarese, Sunnie S. Y. Kim, Michael Maire +2
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maxi…
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
Tri Huynh, Simon Kornblith, Matthew R. Walter +2
Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs…
Orthogonalized SGD and Nested Architectures for Anytime Neural Networks
Chengcheng Wan, Henry Hoffmann, Shan Lu +1
We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over…
Growing Efficient Deep Networks by Structured Continuous Sparsification
Xin Yuan, Pedro Savarese, Michael Maire
We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pr…
Pixel Consensus Voting for Panoptic Segmentation
Haochen Wang, Ruotian Luo, Michael Maire +1
The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform. Pixels cast discretized, probabilistic votes fo…
Winning the Lottery with Continuous Sparsification
Pedro Savarese, Hugo Silva, Michael Maire
The search for efficient, sparse deep neural network models is most prominently performed by pruning: training a dense, overparameterized network and removing parameters, usually v…
Domain-independent Dominance of Adaptive Methods
Pedro Savarese, David McAllester, Sudarshan Babu +1
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that th…
ALERT: Accurate Learning for Energy and Timeliness
Chengcheng Wan, Muhammad Santriaji, Eri Rogers +3
An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of…
Multigrid Neural Memory
Tri Huynh, Michael Maire, Matthew R. Walter
We introduce a novel approach to endowing neural networks with emergent, long-term, large-scale memory. Distinct from strategies that connect neural networks to external memory ban…
Learning Implicitly Recurrent CNNs Through Parameter Sharing
Pedro Savarese, Michael Maire
We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a g…
Regularizing Deep Networks by Modeling and Predicting Label Structure
Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich
We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit int…
Self-Supervised Relative Depth Learning for Urban Scene Understanding
Huaizu Jiang, Erik Learned-Miller, Gustav Larsson +2
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image…
Colorization as a Proxy Task for Visual Understanding
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has be…
Multigrid Neural Architectures
Tsung-Wei Ke, Michael Maire, Stella X. Yu
We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate acros…
FractalNet: Ultra-Deep Neural Networks without Residuals
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structu…
Learning Representations for Automatic Colorization
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many sce…
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
Takuya Narihira, Michael Maire, Stella X. Yu
We introduce a new approach to intrinsic image decomposition, the task of decomposing a single image into albedo and shading components. Our strategy, which we term direct intrinsi…
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
Michael Maire, Takuya Narihira, Stella X. Yu
Spectral embedding provides a framework for solving perceptual organization problems, including image segmentation and figure/ground organization. From an affinity matrix describin…
Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling
Michael Maire, Stella X. Yu, Pietro Perona
We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code repr…
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin, Michael Maire, Serge Belongie +7
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question…