Author details
Author's Published Works
Scheduled Maintenance on Monday 1/13/2025
Single article sales and account management will be unavailable from 5:00 AM - 7:00 PM ET (09:00 - 23:00 UTC). We apologize for the inconvenience.
Author details
Showing 1-24 of 24 results
- Sort
Sort By
Results
Deciphering ‘What’ and ‘Where’ Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
We present an approach for analyzing grouping information contained within a neural network's activations, per-mitting extraction of spatial layout and semantic segmentation from the behavior of large pre-trained vision models. Unlike prior work, our method conducts a who lis tic analysis of a network's activation state, leveraging features from all layers and obviating the need to guess which par...Show More
Drop-Connect as a Fault-Tolerance Approach for RRAM-based Deep Neural Network Accelerators
Mingyuan Xiang;Xuhan Xie;Pedro Savarese;Xin Yuan;Michael Maire;Yanjing Li
Resistive random-access memory (RRAM) is widely recognized as a promising emerging hardware platform for deep neural networks (DNNs). Yet, due to manufacturing limitations, current RRAM devices are highly susceptible to hardware defects, which poses a significant challenge to their practical applicability. In this paper, we present a machine learning technique that enables the deployment of defect...Show More
Automated Testing of Software that Uses Machine Learning APIs
Chengcheng Wan;Shicheng Liu;Sophie Xie;Yifan Liu;Henry Hoffmann;Michael Maire;Shan Lu
2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
Year: 2022 | Conference Paper |
Cited by: Papers (6)
An increasing number of software applications incorporate machine learning (ML) solutions for cognitive tasks that statistically mimic human behaviors. To test such software, tremendous human effort is needed to design image/text/audio inputs that are relevant to the software, and to judge whether the software is processing these inputs as most human beings do. Even when misbehavior is exposed, it...Show More
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
Tri Huynh;Simon Kornblith;Matthew R. Walter;Michael Maire;Maryam Khademi
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2022 | Conference Paper |
Cited by: Papers (75)
Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While positive pairs can be generated reliably (e.g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from...Show More
Domain-Independent Dominance of Adaptive Methods
Pedro Savarese;David McAllester;Sudarshan Babu;Michael Maire
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2021 | Conference Paper |
Cited by: Papers (7)
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 the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. In light of this observation, we demonstrate that, against conventional wisdom, A...Show More
Information-Theoretic Segmentation by Inpainting Error Maximization
Pedro Savarese;Sunnie S. Y. Kim;Michael Maire;Greg Shakhnarovich;David McAllester
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2021 | Conference Paper |
Cited by: Papers (12)
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search proces...Show More
Multimodal Contrastive Training for Visual Representation Learning
Xin Yuan;Zhe Lin;Jason Kuen;Jianming Zhang;Yilin Wang;Michael Maire;Ajinkya Kale;Baldo Faieta
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2021 | Conference Paper |
Cited by: Papers (80)
We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy prediction task in a single domain, our method exploits intrinsic data properties within each modality and semantic information from cross-modal correlation sim...Show More
Are Machine Learning Cloud APIs Used Correctly?
Chengcheng Wan;Shicheng Liu;Henry Hoffmann;Michael Maire;Shan Lu
2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)
Year: 2021 | Conference Paper |
Cited by: Papers (18)
Machine learning (ML) cloud APIs enable developers to easily incorporate learning solutions into software systems. Unfortunately, ML APIs are challenging to use correctly and efficiently, given their unique semantics, data requirements, and accuracy-performance tradeoffs. Much prior work has studied how to develop ML APIs or ML cloud services, but not how open-source applications are using ML APIs...Show More
A Replication of Are Machine Learning Cloud APIs Used Correctly
Chengcheng Wan;Shicheng Liu;Henry Hoffmann;Michael Maire;Shan Lu
2021 IEEE/ACM 43rd International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
Year: 2021 | Conference Paper |
This artifact aims to provide benchmark suite, data, and script used in our study "Are Machine Learning Cloud APIs Used Correctly?". We collected a suite of 360 non-trivial applications that use ML cloud APIs for manual study. We also developed checkers and tool to detect and fix API mis-uses. We hope this artifact can motivate and help future research to further tackle ML API mis-uses. All relate...Show More
Pixel Consensus Voting for Panoptic Segmentation
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2020 | Conference Paper |
Cited by: Papers (22)
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 for the likely regions that contain instance centroids. At the detected peaks that emerge in the voting heatmap, backprojection is applied to collect pixels and produce instance masks. Unlike a sliding window detector that...Show More
Regularizing Deep Networks by Modeling and Predicting Label Structure
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Year: 2018 | Conference Paper |
Cited by: Papers (16)
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 internal structure; we derive a regularizer by learning an autoencoder over the set of annotations. Training thereby becomes a two-phase procedure. The first phase models labels with an autoencoder. The second phase trains ...Show More
Multigrid Neural Architectures
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2017 | Conference Paper |
Cited by: Papers (41)
We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate across scale space, on a pyramid of grids. They consume multigrid inputs and produce multigrid outputs, convolutional filters themselves have both within-scale and cross-scale extent. This aspect is distinct from simple multi...Show More
Colorization as a Proxy Task for Visual Understanding
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2017 | Conference Paper |
Cited by: Papers (301)
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 been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On V...Show More
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2016 | Conference Paper |
Spectral embedding provides a framework for solving perceptual organization problems, including image segmentation and figure/ground organization. From an affinity matrix describing pairwise relationships between pixels, it clusters pixels into regions, and, using a complex-valued extension, orders pixels according to layer. We train a convolutional neural network (CNN) to directly predict the pai...Show More
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression
2015 IEEE International Conference on Computer Vision (ICCV)
Year: 2015 | Conference Paper |
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 intrinsics, is to learn a convolutional neural network (CNN) that directly predicts output albedo and shading channels from an input RGB image patch. Direct intrinsics is a departure from classical techniques for intrinsic image...Show More
Learning lightness from human judgement on relative reflectance
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2015 | Conference Paper |
We develop a new approach to inferring lightness, the perceived reflectance of surfaces, from a single image. Classic methods view this problem from the perspective of intrinsic image decomposition, where an image is separated into reflectance and shading components. Rather than reason about reflectance and shading together, we learn to directly predict lightness differences between pixels. Large-...Show More
Progressive Multigrid Eigensolvers for Multiscale Spectral Segmentation
2013 IEEE International Conference on Computer Vision
Year: 2013 | Conference Paper |
Cited by: Papers (15)
We reexamine the role of multiscale cues in image segmentation using an architecture that constructs a globally coherent scale-space output representation. This characteristic is in contrast to many existing works on bottom-up segmentation, which prematurely compress information into a single scale. The architecture is a standard extension of Normalized Cuts from an image plane to an image pyramid...Show More
Object detection and segmentation from joint embedding of parts and pixels
2011 International Conference on Computer Vision
Year: 2011 | Conference Paper |
Cited by: Papers (38)
We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This framework serves as a perceptual organization stage that integrates information from low-level image cues with that of high-level part detectors. Pixels and parts each appear as nodes in a graph whose edges encode both affinity...Show More
Occlusion boundary detection and figure/ground assignment from optical flow
Patrik Sundberg;Thomas Brox;Michael Maire;Pablo Arbeláez;Jitendra Malik
In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow. This detector outperforms the state-of-the-art on the benchmark of Stein and Hebert, improving average precision from .58 to .72. Moreover, the optical flow on and near occlusion boundaries allows us to assign a depth...Show More
Contour Detection and Hierarchical Image Segmentation
Pablo Arbeláez;Michael Maire;Charless Fowlkes;Jitendra Malik
This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into ...Show More
From contours to regions: An empirical evaluation
Pablo Arbelaez;Michael Maire;Charless Fowlkes;Jitendra Malik
2009 IEEE Conference on Computer Vision and Pattern Recognition
Year: 2009 | Conference Paper |
We propose a generic grouping algorithm that constructs a hierarchy of regions from the output of any contour detector. Our method consists of two steps, an oriented watershed transform (OWT) to form initial regions from contours, followed by construction of an ultra-metric contour map (UCM) defining a hierarchical segmentation. We provide extensive experimental evaluation to demonstrate that, whe...Show More
Using contours to detect and localize junctions in natural images
Michael Maire;Pablo Arbelaez;Charless Fowlkes;Jitendra Malik
2008 IEEE Conference on Computer Vision and Pattern Recognition
Year: 2008 | Conference Paper |
Cited by: Papers (270)
Contours and junctions are important cues for perceptual organization and shape recognition. Detecting junctions locally has proved problematic because the image intensity surface is confusing in the neighborhood of a junction. Edge detectors also do not perform well near junctions. Current leading approaches to junction detection, such as the Harris operator, are based on 2D variation in the inte...Show More
SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition
2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
Year: 2006 | Conference Paper |
We consider visual category recognition in the framework of measuring similarities, or equivalently perceptual distances, to prototype examples of categories. This approach is quite flexible, and permits recognition based on color, texture, and particularly shape, in a homogeneous framework. While nearest neighbor classifiers are natural in this setting, they suffer from the problem of high varian...Show More
Names and faces in the news
T.L. Berg;A.C. Berg;J. Edwards;M. Maire;R. White;Yee-Whye Teh;E. Learned-Miller;D.A. Forsyth
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
Year: 2004 | Conference Paper |
We show quite good face clustering is possible for a dataset of inaccurately and ambiguously labelled face images. Our dataset is 44,773 face images, obtained by applying a face finder to approximately half a million captioned news images. This dataset is more realistic than usual face recognition datasets, because it contains faces captured "in the wild" in a variety of configurations with respec...Show More
IEEE Account
Purchase Details
Profile Information
Need Help?
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Contact Us
- Help
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Sitemap
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.