Search Results for author: Dimitris Samaras

Found 105 papers, 33 papers with code

Self-supervised co-salient object detection via feature correspondence at multiple scales

1 code implementation17 Mar 2024 Souradeep Chakraborty, Dimitris Samaras

Extensive experiments on three CoSOD benchmark datasets show that our self-supervised model outperforms the corresponding state-of-the-art models by a huge margin (e. g. on the CoCA dataset, our model has a 13. 7% F-measure gain over the SOTA unsupervised CoSOD model).

Co-Salient Object Detection object-detection +1

Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos

no code implementations6 Feb 2024 Alfredo Rivero, ShahRukh Athar, Zhixin Shu, Dimitris Samaras

Using a set of control signals, such as head pose and expressions, we transform them to the 3D space with learned deformations to generate the desired rendering.

SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology

no code implementations22 Dec 2023 Saarthak Kapse, Pushpak Pati, Srijan Das, Jingwei Zhang, Chao Chen, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras, Rajarsi R. Gupta, Prateek Prasanna

Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides.

Multiple Instance Learning

Unsupervised and semi-supervised co-salient object detection via segmentation frequency statistics

no code implementations11 Nov 2023 Souradeep Chakraborty, Shujon Naha, Muhammet Bastan, Amit Kumar K C, Dimitris Samaras

Our unsupervised model is a great pre-training initialization for our semi-supervised model SS-CoSOD, especially when very limited labeled data is available for training.

Co-Salient Object Detection object-detection +1

Zero-Shot Object Counting with Language-Vision Models

no code implementations22 Sep 2023 Jingyi Xu, Hieu Le, Dimitris Samaras

Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time.

Object Object Counting

Controllable Dynamic Appearance for Neural 3D Portraits

no code implementations20 Sep 2023 ShahRukh Athar, Zhixin Shu, Zexiang Xu, Fujun Luan, Sai Bi, Kalyan Sunkavalli, Dimitris Samaras

The surface normals prediction is guided using 3DMM normals that act as a coarse prior for the normals of the human head, where direct prediction of normals is hard due to rigid and non-rigid deformations induced by head-pose and facial expression changes.

Learning from Pseudo-labeled Segmentation for Multi-Class Object Counting

no code implementations15 Jul 2023 Jingyi Xu, Hieu Le, Dimitris Samaras

In this paper, we point out that the task of counting objects of interest when there are multiple object classes in the image (namely, multi-class object counting) is particularly challenging for current object counting models.

Object Object Counting +1

SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology

no code implementations12 Jul 2023 Jingwei Zhang, Ke Ma, Saarthak Kapse, Joel Saltz, Maria Vakalopoulou, Prateek Prasanna, Dimitris Samaras

On these two datasets, the proposed additional pathology foundation model further achieves a relative improvement of 5. 07% to 5. 12% in Dice score and 4. 50% to 8. 48% in IOU.

Instance Segmentation Segmentation +1

Conditional Generation from Unconditional Diffusion Models using Denoiser Representations

1 code implementation2 Jun 2023 Alexandros Graikos, Srikar Yellapragada, Dimitris Samaras

Our approach provides a powerful and flexible way to adapt diffusion models to new conditions and generate high-quality augmented data for various conditional generation tasks.

Attribute Data Augmentation +1

AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction

no code implementations CVPR 2023 Aggelina Chatziagapi, Dimitris Samaras

In this work, we present a multimodal solution to the problem of 4D face reconstruction from monocular videos.

3D Face Reconstruction

Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection

no code implementations CVPR 2023 Jingyi Xu, Hieu Le, Dimitris Samaras

To mitigate this issue, we propose a novel variational autoencoder (VAE) based data generation model, which is capable of generating data with increased crop-related diversity.

Few-Shot Object Detection object-detection

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

1 code implementation CVPR 2023 Sounak Mondal, Zhibo Yang, Seoyoung Ahn, Dimitris Samaras, Gregory Zelinsky, Minh Hoai

In response, we pose a new task called ZeroGaze, a new variant of zero-shot learning where gaze is predicted for never-before-searched objects, and we develop a novel model, Gazeformer, to solve the ZeroGaze problem.

Gaze Prediction Language Modelling +2

Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning

1 code implementation21 Mar 2023 Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras

Compared to conventional full fine-tuning approaches, we fine-tune less than 1. 3% of the parameters, yet achieve a relative improvement of 1. 29%-13. 61% in accuracy and 3. 22%-27. 18% in AUROC and reduce GPU memory consumption by 38%-45% while training 21%-27% faster.

Predicting Human Attention using Computational Attention

no code implementations16 Mar 2023 Zhibo Yang, Sounak Mondal, Seoyoung Ahn, Gregory Zelinsky, Minh Hoai, Dimitris Samaras

Most models of visual attention are aimed at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks.

Token Sparsification for Faster Medical Image Segmentation

1 code implementation11 Mar 2023 Lei Zhou, Huidong Liu, Joseph Bae, Junjun He, Dimitris Samaras, Prateek Prasanna

To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline.

Image Segmentation Medical Image Segmentation +2

Zero-shot Object Counting

1 code implementation CVPR 2023 Jingyi Xu, Hieu Le, Vu Nguyen, Viresh Ranjan, Dimitris Samaras

By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting.

Object Object Counting +1

Local Learning on Transformers via Feature Reconstruction

no code implementations29 Dec 2022 Priyank Pathak, Jingwei Zhang, Dimitris Samaras

In this paper, we propose a new mechanism for each local module, where instead of reconstructing the entire image, we reconstruct its input features, generated from previous modules.

Precise Location Matching Improves Dense Contrastive Learning in Digital Pathology

1 code implementation23 Dec 2022 Jingwei Zhang, Saarthak Kapse, Ke Ma, Prateek Prasanna, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras

Our method outperforms previous dense matching methods by up to 7. 2% in average precision for detection and 5. 6% in average precision for instance segmentation tasks.

Contrastive Learning Instance Segmentation +2

Patch-level Gaze Distribution Prediction for Gaze Following

1 code implementation20 Nov 2022 Qiaomu Miao, Minh Hoai, Dimitris Samaras

Gaze following aims to predict where a person is looking in a scene, by predicting the target location, or indicating that the target is located outside the image.

Binary Classification

Unraveling Key Elements Underlying Molecular Property Prediction: A Systematic Study

1 code implementation26 Sep 2022 Jianyuan Deng, Zhibo Yang, Hehe Wang, Iwao Ojima, Dimitris Samaras, Fusheng Wang

Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature.

Drug Discovery Molecular Property Prediction +3

Gigapixel Whole-Slide Images Classification using Locally Supervised Learning

1 code implementation17 Jul 2022 Jingwei Zhang, Xin Zhang, Ke Ma, Rajarsi Gupta, Joel Saltz, Maria Vakalopoulou, Dimitris Samaras

Histopathology whole slide images (WSIs) play a very important role in clinical studies and serve as the gold standard for many cancer diagnoses.

Classification Multiple Instance Learning +1

Target-absent Human Attention

1 code implementation4 Jul 2022 Zhibo Yang, Sounak Mondal, Seoyoung Ahn, Gregory Zelinsky, Minh Hoai, Dimitris Samaras

In this paper, we propose the first data-driven computational model that addresses the search-termination problem and predicts the scanpath of search fixations made by people searching for targets that do not appear in images.

Imitation Learning

Diffusion models as plug-and-play priors

1 code implementation17 Jun 2022 Alexandros Graikos, Nikolay Malkin, Nebojsa Jojic, Dimitris Samaras

We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional information $\mathbf{y}$.

Combinatorial Optimization Denoising +2

Learning Probabilistic Topological Representations Using Discrete Morse Theory

no code implementations3 Jun 2022 Xiaoling Hu, Dimitris Samaras, Chao Chen

We use discrete Morse theory and persistent homology to construct an one-parameter family of structures as the topological/structural representation space.

Image Segmentation Semantic Segmentation

Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation

1 code implementation10 Mar 2022 Lei Zhou, Huidong Liu, Joseph Bae, Junjun He, Dimitris Samaras, Prateek Prasanna

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis.

Brain Tumor Segmentation Image Classification +4

Visual attention analysis of pathologists examining whole slide images of Prostate cancer

no code implementations17 Feb 2022 Souradeep Chakraborty, Ke Ma, Rajarsi Gupta, Beatrice Knudsen, Gregory J. Zelinsky, Joel H. Saltz, Dimitris Samaras

To quantify the relationship between a pathologist's attention and evidence for cancer in the WSI, we obtained tumor annotations from a genitourinary specialist.

Navigate whole slide images

Efficient Semi-Discrete Optimal Transport Using the Maximum Relative Error between Distributions

no code implementations29 Sep 2021 Huidong Liu, Ke Ma, Lei Zhou, Dimitris Samaras

If the \texttt{MRE} is smaller than 1, then every target point is guaranteed to have an area in the source distribution that is mapped to it.

Learning Surface Parameterization for Document Image Unwarping

no code implementations29 Sep 2021 Sagnik Das, Ke Ma, Zhixin Shu, Dimitris Samaras

We also demonstrate the usefulness of our system by applying it to document texture editing.

3D Scene Reconstruction

FLAME-in-NeRF: Neural control of Radiance Fields for Free View Face Animation

no code implementations29 Sep 2021 ShahRukh Athar, Zhixin Shu, Dimitris Samaras

In this work, we design a system that enables 1) novel view synthesis for portrait video, of both the human subject and the scene they are in and 2) explicit control of the facial expressions through a low-dimensional expression representation.

Neural Rendering Novel View Synthesis

SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery

no code implementations11 Aug 2021 Aggelina Chatziagapi, ShahRukh Athar, Francesc Moreno-Noguer, Dimitris Samaras

We present SIDER(Single-Image neural optimization for facial geometric DEtail Recovery), a novel photometric optimization method that recovers detailed facial geometry from a single image in an unsupervised manner.

FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animation

no code implementations10 Aug 2021 ShahRukh Athar, Zhixin Shu, Dimitris Samaras

In this work, we design a system that enables both novel view synthesis for portrait video, including the human subject and the scene background, and explicit control of the facial expressions through a low-dimensional expression representation.

Face Model Neural Rendering +1

Temporal Feature Warping for Video Shadow Detection

no code implementations29 Jul 2021 Shilin Hu, Hieu Le, Dimitris Samaras

The current video shadow detection method achieves this goal via co-attention, which mostly exploits information that is temporally coherent but is not robust in detecting moving shadows and small shadow regions.

Optical Flow Estimation Shadow Detection

Attention based CNN-LSTM Network for Pulmonary Embolism Prediction on Chest Computed Tomography Pulmonary Angiograms

no code implementations13 Jul 2021 Sudhir Suman, Gagandeep Singh, Nicole Sakla, Rishabh Gattu, Jeremy Green, Tej Phatak, Dimitris Samaras, Prateek Prasanna

In this study we propose a two-stage attention-based CNN-LSTM network for predicting PE, its associated type (chronic, acute) and corresponding location (leftsided, rightsided or central) on computed tomography (CT) examinations.

Computed Tomography (CT)

Hierarchical Proxy-based Loss for Deep Metric Learning

no code implementations25 Mar 2021 Zhibo Yang, Muhammet Bastan, Xinliang Zhu, Doug Gray, Dimitris Samaras

In this paper, we present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss.

Image Retrieval Metric Learning +1

Topology-Aware Segmentation Using Discrete Morse Theory

no code implementations ICLR 2021 Xiaoling Hu, Yusu Wang, Li Fuxin, Dimitris Samaras, Chao Chen

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern.

Image Segmentation Segmentation +1

End-to-End Piece-Wise Unwarping of Document Images

no code implementations ICCV 2021 Sagnik Das, Kunwar Yashraj Singh, Jon Wu, Erhan Bas, Vijay Mahadevan, Rahul Bhotika, Dimitris Samaras

Document unwarping attempts to undo the physical deformation of the paper and recover a 'flatbed' scanned document-image for downstream tasks such as OCR.

MS-SSIM Optical Character Recognition (OCR) +1

Localization in the Crowd with Topological Constraints

1 code implementation23 Dec 2020 Shahira Abousamra, Minh Hoai, Dimitris Samaras, Chao Chen

Due to various challenges, a localization method is prone to spatial semantic errors, i. e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region.

Crowd Counting

Physics-based Shadow Image Decomposition for Shadow Removal

2 code implementations23 Dec 2020 Hieu Le, Dimitris Samaras

Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer.

Shadow Removal

Modeling Deep Learning Based Privacy Attacks on Physical Mail

1 code implementation22 Dec 2020 Bingyao Huang, Ruyi Lian, Dimitris Samaras, Haibin Ling

Mail privacy protection aims to prevent unauthorized access to hidden content within an envelope since normal paper envelopes are not as safe as we think.

Denoising Image Dehazing

FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction

no code implementations14 Dec 2020 ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer, Dimitris Samaras

The facial details are represented as a vertex displacement map and used then by a Neural Renderer to photo-realistically render novel images of any single image in any desired expression and view.

Intrinsic Decomposition of Document Images In-the-Wild

1 code implementation29 Nov 2020 Sagnik Das, Hassan Ahmed Sial, Ke Ma, Ramon Baldrich, Maria Vanrell, Dimitris Samaras

However, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and textures and; (b) synthetic or hybrid datasets with non-realistic, simulated lighting conditions are used to train the models.

Document Shadow Removal Intrinsic Image Decomposition +1

Learning Clusterable Visual Features for Zero-Shot Recognition

no code implementations7 Oct 2020 Jingyi Xu, Zhixin Shu, Dimitris Samaras

However, some testing data are considered "hard" as they lie close to the decision boundaries and are prone to misclassification, leading to performance degradation for ZSL.

Classification Few-Shot Learning +2

Distribution Matching for Crowd Counting

1 code implementation NeurIPS 2020 Boyu Wang, Huidong Liu, Dimitris Samaras, Minh Hoai

Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point.

Crowd Counting

Light Direction and Color Estimation from Single Image with Deep Regression

no code implementations18 Sep 2020 Hassan A. Sial, Ramon Baldrich, Maria Vanrell, Dimitris Samaras

We present a method to estimate the direction and color of the scene light source from a single image.

regression

A Study of Human Gaze Behavior During Visual Crowd Counting

no code implementations14 Sep 2020 Raji Annadi, Yupei Chen, Viresh Ranjan, Dimitris Samaras, Gregory Zelinsky, Minh Hoai

Analyzing the collected gaze behavior of ten human participants on thirty crowd images, we observe some common approaches for visual counting.

Crowd Counting

From Shadow Segmentation to Shadow Removal

no code implementations ECCV 2020 Hieu Le, Dimitris Samaras

Our method achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images.

Segmentation Shadow Removal

Towards Better Opioid Antagonists Using Deep Reinforcement Learning

no code implementations26 Mar 2020 Jianyuan Deng, Zhibo Yang, Yao Li, Dimitris Samaras, Fusheng Wang

Naloxone, an opioid antagonist, has been widely used to save lives from opioid overdose, a leading cause for death in the opioid epidemic.

Drug Discovery reinforcement-learning +2

Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images of 10 Cancer Types

1 code implementation18 Feb 2020 Le Hou, Rajarsi Gupta, John S. Van Arnam, Yuwei Zhang, Kaustubh Sivalenka, Dimitris Samaras, Tahsin M. Kurc, Joel H. Saltz

To address this, we developed an analysis pipeline that segments nuclei in whole slide tissue images from multiple cancer types with a quality control process.

Segmentation

Self-supervised Deformation Modeling for Facial Expression Editing

no code implementations2 Nov 2019 ShahRukh Athar, Zhixin Shu, Dimitris Samaras

In the "motion-editing" step, we explicitly model facial movement through image deformation, warping the image into the desired expression.

Disentanglement Facial Editing +2

Exascale Deep Learning to Accelerate Cancer Research

no code implementations26 Sep 2019 Robert M. Patton, J. Travis Johnston, Steven R. Young, Catherine D. Schuman, Thomas E. Potok, Derek C. Rose, Seung-Hwan Lim, Junghoon Chae, Le Hou, Shahira Abousamra, Dimitris Samaras, Joel Saltz

Using MENNDL--an HPC-enabled software stack for neural architecture search--we generate a neural network with comparable accuracy to state-of-the-art networks on a cancer pathology dataset that is also $16\times$ faster at inference.

Neural Architecture Search

Shadow Removal via Shadow Image Decomposition

3 code implementations ICCV 2019 Hieu Le, Dimitris Samaras

Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7. 4.

Shadow Removal

Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types

no code implementations9 Jul 2019 Shahira Abousamra, Le Hou, Rajarsi Gupta, Chao Chen, Dimitris Samaras, Tahsin Kurc, Rebecca Batiste, Tianhao Zhao, Shroyer Kenneth, Joel Saltz

This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment.

General Classification

Topology-Preserving Deep Image Segmentation

2 code implementations NeurIPS 2019 Xiaoling Hu, Li Fuxin, Dimitris Samaras, Chao Chen

Segmentation algorithms are prone to make topological errors on fine-scale structures, e. g., broken connections.

Image Segmentation Segmentation +1

Weakly Labeling the Antarctic: The Penguin Colony Case

no code implementations8 May 2019 Hieu Le, Bento Gonçalves, Dimitris Samaras, Heather Lynch

This segmentation network is trained with a specific loss function, based on the average activation, to effectively learn from the data with the weakly-annotated labels.

Segmentation Semantic Segmentation

Label Super Resolution with Inter-Instance Loss

no code implementations9 Apr 2019 Maozheng Zhao, Le Hou, Han Le, Dimitris Samaras, Nebojsa Jojic, Danielle Fassler, Tahsin Kurc, Rajarsi Gupta, Kolya Malkin, Shroyer Kenneth, Joel Saltz

On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient.

Segmentation Semantic Segmentation +1

Sequence-to-Segment Networks for Segment Detection

no code implementations NeurIPS 2018 Zijun Wei, Boyu Wang, Minh Hoai Nguyen, Jianming Zhang, Zhe Lin, Xiaohui Shen, Radomir Mech, Dimitris Samaras

Detecting segments of interest from an input sequence is a challenging problem which often requires not only good knowledge of individual target segments, but also contextual understanding of the entire input sequence and the relationships between the target segments.

Temporal Action Proposal Generation Video Summarization

Latent Space Optimal Transport for Generative Models

no code implementations16 Sep 2018 Huidong Liu, Yang Guo, Na lei, Zhixin Shu, Shing-Tung Yau, Dimitris Samaras, Xianfeng GU

Experimental results on an eight-Gaussian dataset show that the proposed OT can handle multi-cluster distributions.

A Two-Step Computation of the Exact GAN Wasserstein Distance

no code implementations ICML 2018 Huidong Liu, Xianfeng GU, Dimitris Samaras

In this paper, we propose a two-step method to compute the Wasserstein distance in Wasserstein Generative Adversarial Networks (WGANs): 1) The convex part of our objective can be solved by linear programming; 2) The non-convex residual can be approximated by a deep neural network.

Vocal Bursts Valence Prediction

DocUNet: Document Image Unwarping via a Stacked U-Net

1 code implementation CVPR 2018 Ke Ma, Zhixin Shu, Xue Bai, Jue Wang, Dimitris Samaras

The network is trained on this dataset with various data augmentations to improve its generalization ability.

Ranked #4 on SSIM on DocUNet (using extra training data)

Local Distortion MS-SSIM +1

Unsupervised Histopathology Image Synthesis

no code implementations13 Dec 2017 Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M. Kurc, Rajarsi R. Gupta, Joel H. Saltz

We propose a unified pipeline that: a) generates a set of initial synthetic histopathology images with paired information about the nuclei such as segmentation masks; b) refines the initial synthetic images through a Generative Adversarial Network (GAN) to reference styles; c) trains a task-specific CNN and boosts the performance of the task-specific CNN with on-the-fly generated adversarial examples.

Generative Adversarial Network Image Generation

A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation

1 code implementation ECCV 2018 Hieu Le, Tomas F. Yago Vicente, Vu Nguyen, Minh Hoai, Dimitris Samaras

The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions.

Detecting Shadows Shadow Detection

An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations

no code implementations28 Nov 2017 Mengjiao Wang, Zhixin Shu, Shiyang Cheng, Yannis Panagakis, Dimitris Samaras, Stefanos Zafeiriou

Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others.

3D Face Reconstruction

Shadow Detection With Conditional Generative Adversarial Networks

no code implementations ICCV 2017 Vu Nguyen, Tomas F. Yago Vicente, Maozheng Zhao, Minh Hoai, Dimitris Samaras

We introduce scGAN, a novel extension of conditional Generative Adversarial Networks (GAN) tailored for the challenging problem of shadow detection in images.

Shadow Detection

Improving Heterogeneous Face Recognition with Conditional Adversarial Networks

no code implementations8 Sep 2017 Wuming Zhang, Zhixin Shu, Dimitris Samaras, Liming Chen

Heterogeneous face recognition between color image and depth image is a much desired capacity for real world applications where shape information is looked upon as merely involved in gallery.

Face Recognition Heterogeneous Face Recognition +1

Neural Face Editing with Intrinsic Image Disentangling

2 code implementations CVPR 2017 Zhixin Shu, Ersin Yumer, Sunil Hadap, Kalyan Sunkavalli, Eli Shechtman, Dimitris Samaras

Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other --- a process that is tedious, fragile, and computationally intensive.

Facial Editing Generative Adversarial Network

Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images

no code implementations3 Apr 2017 Le Hou, Vu Nguyen, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, Tianhao Zhao, Joel H. Saltz

In this work, we propose a sparse Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images.

Geodesic Distance Histogram Feature for Video Segmentation

no code implementations31 Mar 2017 Hieu Le, Vu Nguyen, Chen-Ping Yu, Dimitris Samaras

This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms.

Segmentation Superpixels +2

Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images

no code implementations20 Dec 2016 Veda Murthy, Le Hou, Dimitris Samaras, Tahsin M. Kurc, Joel H. Saltz

Classifying the various shapes and attributes of a glioma cell nucleus is crucial for diagnosis and understanding the disease.

Attribute General Classification

Learned Region Sparsity and Diversity Also Predicts Visual Attention

no code implementations NeurIPS 2016 Zijun Wei, Hossein Adeli, Minh Hoai Nguyen, Greg Zelinsky, Dimitris Samaras

Learned region sparsity has achieved state-of-the-art performance in classification tasks by exploiting and integrating a sparse set of local information into global decisions.

General Classification

Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks

3 code implementations17 Nov 2016 Le Hou, Chen-Ping Yu, Dimitris Samaras

In this work, we propose to leverage these relationships between classes by training deep nets with the exact squared Earth Mover's Distance (also known as Wasserstein distance) for single-label classification.

Age Classification General Classification

Efficient Video Segmentation Using Parametric Graph Partitioning

no code implementations ICCV 2015 Chen-Ping Yu, Hieu Le, Gregory Zelinsky, Dimitris Samaras

Video segmentation is the task of grouping similar pixels in the spatio-temporal domain, and has become an important preprocessing step for subsequent video analysis.

Clustering Computational Efficiency +4

Leave-One-Out Kernel Optimization for Shadow Detection

no code implementations ICCV 2015 Tomas F. Yago Vicente, Minh Hoai, Dimitris Samaras

Optimizing the leave-one-out cross validation error is typically difficult, but it can be done efficiently in our framework.

Shadow Detection Superpixels

Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification

1 code implementation CVPR 2016 Le Hou, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, James E. Davis, Joel H. Saltz

However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible.

Classification General Classification +1

Region segmentation for sparse decompositions: better brain parcellations from rest fMRI

no code implementations12 Dec 2014 Alexandre Abraham, Elvis Dohmatob, Bertrand Thirion, Dimitris Samaras, Gael Varoquaux

Functional Magnetic Resonance Images acquired during resting-state provide information about the functional organization of the brain through measuring correlations between brain areas.

The Photometry of Intrinsic Images

no code implementations CVPR 2014 Marc Serra, Olivier Penacchio, Robert Benavente, Maria Vanrell, Dimitris Samaras

The proposed mathematical formulation includes information about the color of the illuminant and the effects of the camera sensors, both of which modify the observed color of the reflectance of the objects in the scene during the acquisition process.

3D Reconstruction Color Constancy +2

Modeling Clutter Perception using Parametric Proto-object Partitioning

no code implementations NeurIPS 2013 Chen-Ping Yu, Wen-Yu Hua, Dimitris Samaras, Greg Zelinsky

Visual clutter, the perception of an image as being crowded and disordered, affects aspects of our lives ranging from object detection to aesthetics, yet relatively little effort has been made to model this important and ubiquitous percept.

Object object-detection +3

Studying Relationships between Human Gaze, Description, and Computer Vision

no code implementations CVPR 2013 Kiwon Yun, Yifan Peng, Dimitris Samaras, Gregory J. Zelinsky, Tamara L. Berg

We posit that user behavior during natural viewing of images contains an abundance of information about the content of images as well as information related to user intent and user defined content importance.

Sparse and Locally Constant Gaussian Graphical Models

no code implementations NeurIPS 2009 Jean Honorio, Dimitris Samaras, Nikos Paragios, Rita Goldstein, Luis E. Ortiz

Locality information is crucial in datasets where each variable corresponds to a measurement in a manifold (silhouettes, motion trajectories, 2D and 3D images).

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