Search Results for author: Michael Maire

Found 34 papers, 14 papers with code

Residual Connections Harm Self-Supervised Abstract Feature Learning

no code implementations16 Apr 2024 Xiao Zhang, Ruoxi Jiang, William Gao, Rebecca Willett, Michael Maire

We demonstrate that adding a weighting factor to decay the strength of identity shortcuts within residual networks substantially improves semantic feature learning in the state-of-the-art self-supervised masked autoencoding (MAE) paradigm.

Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations

no code implementations11 Dec 2023 Xiao Zhang, David Yunis, Michael Maire

We present an approach for analyzing grouping information contained within a neural network's activations, permitting extraction of spatial layout and semantic segmentation from the behavior of large pre-trained vision models.

Semantic Segmentation

SySMOL: Co-designing Algorithms and Hardware for Neural Networks with Heterogeneous Precisions

no code implementations23 Nov 2023 Cyrus Zhou, Pedro Savarese, Vaughn Richard, Zack Hassman, Xin Yuan, Michael Maire, Michael DiBrino, Yanjing Li

We present an end-to-end co-design approach encompassing computer architecture, training algorithm, and inference optimization to efficiently execute networks with fine-grained heterogeneous precisions.

Inference Optimization Quantization

HyperFields: Towards Zero-Shot Generation of NeRFs from Text

no code implementations26 Oct 2023 Sudarshan Babu, Richard Liu, Avery Zhou, Michael Maire, Greg Shakhnarovich, Rana Hanocka

We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning.

CacheGen: KV Cache Compression and Streaming for Fast Language Model Serving

1 code implementation11 Oct 2023 YuHan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, YuYang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang

Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 5-4. 3x and the total delay in fetching and processing contexts by 3. 2-3. 7x while having negligible impact on the LLM response quality in accuracy or perplexity.

Language Modelling Quantization

Automatic and Efficient Customization of Neural Networks for ML Applications

no code implementations7 Oct 2023 YuHan Liu, Chengcheng Wan, Kuntai Du, Henry Hoffmann, Junchen Jiang, Shan Lu, Michael Maire

ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API.

Structural Adversarial Objectives for Self-Supervised Representation Learning

1 code implementation30 Sep 2023 Xiao Zhang, Michael Maire

Within the framework of generative adversarial networks (GANs), we propose objectives that task the discriminator for self-supervised representation learning via additional structural modeling responsibilities.

Contrastive Learning Data Augmentation +1

Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation

no code implementations27 Sep 2023 Xin Yuan, Michael Maire

We develop a neural network architecture which, trained in an unsupervised manner as a denoising diffusion model, simultaneously learns to both generate and segment images.

Denoising Image Generation +4

Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits

no code implementations31 May 2023 Zhuokai Zhao, Takumi Matsuzawa, William Irvine, Michael Maire, Gordon L Kindlmann

NERO evaluation is consist of a task-agnostic interactive interface and a set of visualizations, called NERO plots, which reveals the equivariance property of the model.

3D Point Cloud Classification object-detection +2

Meta-Learning via Learning with Distributed Memory

no code implementations NeurIPS 2021 Sudarshan Babu, Pedro Savarese, Michael Maire

We demonstrate that efficient meta-learning can be achieved via end-to-end training of deep neural networks with memory distributed across layers.

Few-Shot Semantic Segmentation Meta-Learning +1

Multimodal Contrastive Training for Visual Representation Learning

no code implementations CVPR 2021 Xin Yuan, Zhe Lin, Jason Kuen, Jianming Zhang, Yilin Wang, Michael Maire, Ajinkya Kale, Baldo Faieta

We first train our model on COCO and evaluate the learned visual representations on various downstream tasks including image classification, object detection, and instance segmentation.

Cross-Modal Retrieval Image Classification +6

Information-Theoretic Segmentation by Inpainting Error Maximization

1 code implementation CVPR 2021 Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, David Mcallester

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.

Image Segmentation Segmentation +2

Self-Supervised Visual Representation Learning from Hierarchical Grouping

no code implementations NeurIPS 2020 Xiao Zhang, Michael Maire

We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability.

Representation Learning

Boosting Contrastive Self-Supervised Learning with False Negative Cancellation

1 code implementation23 Nov 2020 Tri Huynh, Simon Kornblith, Matthew R. Walter, Michael Maire, Maryam Khademi

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 different images regardless of their semantic content or visual features.

Contrastive Learning Representation Learning +3

Orthogonalized SGD and Nested Architectures for Anytime Neural Networks

no code implementations ICML 2020 Chengcheng Wan, Henry Hoffmann, Shan Lu, Michael Maire

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 time.

Growing Efficient Deep Networks by Structured Continuous Sparsification

no code implementations ICLR 2021 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.

Image Classification Language Modelling +1

Winning the Lottery with Continuous Sparsification

2 code implementations NeurIPS 2020 Pedro Savarese, Hugo Silva, Michael Maire

Additionally, the recent Lottery Ticket Hypothesis conjectures that, for a typically-sized neural network, it is possible to find small sub-networks which, when trained from scratch on a comparable budget, match the performance of the original dense counterpart.

Network Pruning Ticket Search +1

Domain-independent Dominance of Adaptive Methods

1 code implementation CVPR 2021 Pedro Savarese, David Mcallester, Sudarshan Babu, Michael Maire

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.

Image Classification Language Modelling +1

ALERT: Accurate Learning for Energy and Timeliness

no code implementations31 Oct 2019 Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, Shan Lu

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans.

Image Classification

Multigrid Neural Memory

1 code implementation ICML 2020 Tri Huynh, Michael Maire, Matthew R. Walter

We introduce a novel approach to endowing neural networks with emergent, long-term, large-scale memory.

Question Answering

Regularizing Deep Networks by Modeling and Predicting Label Structure

no code implementations CVPR 2018 Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich

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.

Semantic Segmentation

Sparsely Aggregated Convolutional Networks

2 code implementations ECCV 2018 Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, Ping Tan

We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers.

Multigrid Neural Architectures

1 code implementation CVPR 2017 Tsung-Wei Ke, Michael Maire, Stella X. Yu

Most critically, multigrid structure enables networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which modern CNNs fail.

Image Classification Semantic Segmentation

FractalNet: Ultra-Deep Neural Networks without Residuals

4 code implementations24 May 2016 Gustav Larsson, Michael Maire, Gregory Shakhnarovich

We introduce a design strategy for neural network macro-architecture based on self-similarity.

Image Classification

Learning Representations for Automatic Colorization

3 code implementations22 Mar 2016 Gustav Larsson, Michael Maire, Gregory Shakhnarovich

This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation.

Colorization Image Colorization +1

Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

no code implementations CVPR 2016 Michael Maire, Takuya Narihira, Stella X. Yu

Spectral embedding provides a framework for solving perceptual organization problems, including image segmentation and figure/ground organization.

Edge Detection Image Segmentation +2

Learning Lightness From Human Judgement on Relative Reflectance

no code implementations CVPR 2015 Takuya Narihira, Michael Maire, Stella X. Yu

We develop a new approach to inferring lightness, the perceived reflectance of surfaces, from a single image.

Intrinsic Image Decomposition

Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling

no code implementations16 Oct 2014 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 representation of an image.

Contour Detection Dictionary Learning

Microsoft COCO: Common Objects in Context

35 code implementations1 May 2014 Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár

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 of scene understanding.

Instance Segmentation Object +5

Cannot find the paper you are looking for? You can Submit a new open access paper.