Search Results for author:
Found 91 papers, 28 papers with code
TopoGAN: A Topology-Aware Generative Adversarial Network
We show in experiments that our method generates synthetic images with realistic topology.
AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction
In this work, we present a multimodal solution to the problem of 4D face reconstruction from monocular videos.
Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection
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.
Computational Pathology: A Survey Review and The Way Forward
Computational Pathology (CoPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images.
Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
In digital pathology, the spatial context of cells is important for cell classification, cancer diagnosis and prognosis.
S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces
We thus propose to regularize neural rendering optimization with an MVS solution.
Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention
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.
Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning
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
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
To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline.
Zero-shot Object Counting
By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting.
Local Learning on Transformers via Feature Reconstruction
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
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.
Patch-level Gaze Distribution Prediction for Gaze Following
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.
Taking a Respite from Representation Learning for Molecular Property Prediction
Despite the boom of AI techniques in molecular representation learning, some key aspects underlying molecular property prediction haven't been carefully examined yet.
Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
Histopathology whole slide images (WSIs) play a very important role in clinical studies and serve as the gold standard for many cancer diagnoses.
Target-absent Human Attention
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.
Diffusion models as plug-and-play priors
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 $\mathbf{y}$.
Learning Probabilistic Topological Representations Using Discrete Morse Theory
We use discrete Morse theory and persistent homology to construct an one-parameter family of structures as the topological/structural representation space.
A Novel Framework for Characterization of Tumor-Immune Spatial Relationships in Tumor Microenvironment
Understanding the impact of tumor biology on the composition of nearby cells often requires characterizing the impact of biologically distinct tumor regions.
Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation
Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis.
Visual attention analysis of pathologists examining whole slide images of Prostate cancer
To quantify the relationship between a pathologist's attention and evidence for cancer in the WSI, we obtained tumor annotations from a genitourinary specialist.
Lung Swapping Autoencoder: Learning a Disentangled Structure-texture Representation of Chest Radiographs
Well-labeled datasets of chest radiographs (CXRs) are difficult to acquire due to the high cost of annotation.
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
Labels are costly and sometimes unreliable.
Ranked #5 on
Image Classification
on mini WebVision 1.0
Multi-Class Cell Detection Using Spatial Context Representation
In digital pathology, both detection and classification of cells are important for automatic diagnostic and prognostic tasks.
FLAME-in-NeRF: Neural control of Radiance Fields for Free View Face Animation
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.
Learning Surface Parameterization for Document Image Unwarping
We also demonstrate the usefulness of our system by applying it to document texture editing.
Efficient Semi-Discrete Optimal Transport Using the Maximum Relative Error between Distributions
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.
FaceDet3D: Facial Expressions with 3D Geometric Detail Hallucination
Facial Expressions induce a variety of high-level details on the 3D face geometry.
SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery
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
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.
Temporal Feature Warping for Video Shadow Detection
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.
Attention based CNN-LSTM Network for Pulmonary Embolism Prediction on Chest Computed Tomography Pulmonary Angiograms
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.
A Joint Spatial and Magnification Based Attention Framework for Large Scale Histopathology Classification
To tackle these problems, we propose a novel spatial and magnification based attention sampling strategy.
Artificial Intelligence in Drug Discovery: Applications and Techniques
Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade.
Hierarchical Proxy-based Loss for Deep Metric Learning
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.
Topology-Aware Segmentation Using Discrete Morse Theory
In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern.
End-to-End Piece-Wise Unwarping of Document Images
Document unwarping attempts to undo the physical deformation of the paper and recover a 'flatbed' scanned document-image for downstream tasks such as OCR.
Physics-based Shadow Image Decomposition for Shadow Removal
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.
Ranked #2 on
Shadow Removal
on Adjusted ISTD
Localization in the Crowd with Topological Constraints
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.
Modeling Deep Learning Based Privacy Attacks on Physical Mail
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.
FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction
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
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.
Intrinsic Image Decomposition
Optical Character Recognition (OCR)
+1
Learning Clusterable Visual Features for Zero-Shot Recognition
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.
Variational Feature Disentangling for Fine-Grained Few-Shot Classification
We assume that the distribution of intra-class variance generalizes across the base class and the novel class.
Ranked #13 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
Distribution Matching for Crowd Counting
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.
Ranked #2 on
Crowd Counting
on UCF-QNRF
Light Direction and Color Estimation from Single Image with Deep Regression
We present a method to estimate the direction and color of the scene light source from a single image.
A Study of Human Gaze Behavior During Visual Crowd Counting
Analyzing the collected gaze behavior of ten human participants on thirty crowd images, we observe some common approaches for visual counting.
From Shadow Segmentation to Shadow Removal
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.
Ranked #4 on
Shadow Removal
on Adjusted ISTD
Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning
These maps were learned by IRL and then used to predict behavioral scanpaths for multiple target categories.
Towards Better Opioid Antagonists Using Deep Reinforcement Learning
Naloxone, an opioid antagonist, has been widely used to save lives from opioid overdose, a leading cause for death in the opioid epidemic.
Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images of 10 Cancer Types
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.
Self-supervised Deformation Modeling for Facial Expression Editing
In the "motion-editing" step, we explicitly model facial movement through image deformation, warping the image into the desired expression.
Exascale Deep Learning to Accelerate Cancer Research
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.
Shadow Removal via Shadow Image Decomposition
Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7. 4.
Ranked #3 on
Shadow Removal
on Adjusted ISTD
Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types
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.
Topology-Preserving Deep Image Segmentation
Segmentation algorithms are prone to make topological errors on fine-scale structures, e. g., broken connections.
Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer
Quantitative assessment of Tumor-TIL spatial relationships is increasingly important in both basic science and clinical aspects of breast cancer research.
Weakly Labeling the Antarctic: The Penguin Colony Case
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.
Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion
In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories.
Label Super Resolution with Inter-Instance Loss
On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient.
Sequence-to-Segment Networks for Segment Detection
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.
Latent Space Optimal Transport for Generative Models
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
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.
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner.
Ranked #9 on
Unsupervised Facial Landmark Detection
on MAFL
Good View Hunting: Learning Photo Composition From Dense View Pairs
Finding views with good photo composition is a challenging task for machine learning methods.
DocUNet: Document Image Unwarping via a Stacked U-Net
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)
Unsupervised Histopathology Image Synthesis
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.
A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation
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.
Ranked #4 on
Shadow Detection
on SBU
An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations
Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others.
Shadow Detection With Conditional Generative Adversarial Networks
We introduce scGAN, a novel extension of conditional Generative Adversarial Networks (GAN) tailored for the challenging problem of shadow detection in images.
Ranked #6 on
RGB Salient Object Detection
on ISTD
Improving Heterogeneous Face Recognition with Conditional Adversarial Networks
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.
Neural Face Editing with Intrinsic Image Disentangling
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.
Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images
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
This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms.
Ranked #1 on
Video Segmentation
on SegTrack v2
Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images
Classifying the various shapes and attributes of a glioma cell nucleus is crucial for diagnosis and understanding the disease.
Co-localization with Category-Consistent Features and Geodesic Distance Propagation
Co-localization is the problem of localizing objects of the same class using only the set of images that contain them.
Ranked #1 on
Object Localization
on PASCAL VOC 2012
Learned Region Sparsity and Diversity Also Predicts Visual Attention
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.
Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example
These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas.
Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks
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.
Neural Networks with Smooth Adaptive Activation Functions for Regression
In this paper, we propose and apply AAFs on feedforward NNs for regression tasks.
Noisy Label Recovery for Shadow Detection in Unfamiliar Domains
However, shadow detection on broader image domains is still challenging due to the lack of annotated training data.
Leave-One-Out Kernel Optimization for Shadow Detection
Optimizing the leave-one-out cross validation error is typically difficult, but it can be done efficiently in our framework.
Efficient Video Segmentation Using Parametric Graph Partitioning
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.
Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification
However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible.
Region segmentation for sparse decompositions: better brain parcellations from rest fMRI
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
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.
Modeling Clutter Perception using Parametric Proto-object Partitioning
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.
Studying Relationships between Human Gaze, Description, and Computer Vision
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.
On the Statistical Efficiency of $\ell_{1,p}$ Multi-Task Learning of Gaussian Graphical Models
In this paper, we present $\ell_{1, p}$ multi-task structure learning for Gaussian graphical models.
Sparse and Locally Constant Gaussian Graphical Models
Locality information is crucial in datasets where each variable corresponds to a measurement in a manifold (silhouettes, motion trajectories, 2D and 3D images).
