Search Results for author:
Found 44 papers, 19 papers with code
Leveraging Latents for Efficient Thermography Classification and Segmentation
In this work, we present a novel algorithm for both breast cancer classification and segmentation.
Active propulsion noise shaping for multi-rotor aircraft localization
Multi-rotor aerial autonomous vehicles (MAVs) primarily rely on vision for navigation purposes.
Classifier Robustness Enhancement Via Test-Time Transformation
We show that the proposed method achieves state-of-the-art results and validate our claim through extensive experiments on a variety of defense methods, classifier architectures, and datasets.
Multi PILOT: Learned Feasible Multiple Acquisition Trajectories for Dynamic MRI
Several studies have particularly focused on applying deep learning techniques to learn these acquisition trajectories in order to attain better image reconstruction, rather than using some predefined set of trajectories.
Threat Model-Agnostic Adversarial Defense using Diffusion Models
Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks.
Joint optimization of system design and reconstruction in MIMO radar imaging
Inspired by these successes, in this work, we propose to learn MIMO acquisition parameters in the form of receive (Rx) antenna elements locations jointly with an image neural-network based reconstruction.
GRASP: Graph Alignment through Spectral Signatures
In this paper, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs.
Detector-Free Weakly Supervised Grounding by Separation
In this work, we focus on the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained detector.
Ranked #1 on
Phrase Grounding
on Visual Genome
Self-Supervised Classification Network
To guarantee non-degenerate solutions (i. e., solutions where all labels are assigned to the same class) we propose a mathematically motivated variant of the cross-entropy loss that has a uniform prior asserted on the predicted labels.
Ranked #3 on
Unsupervised Image Classification
on ImageNet
ISP Distillation
We then train a model that is applied directly to the RAW data by using knowledge distillation such that the model predictions for RAW images will be aligned with the predictions of an off-the-shelf pre-trained model for processed RGB images.
Non-Rigid Puzzles
We assume to be given a reference shape and its multiple parts undergoing a non-rigid deformation.
3D FLAT: Feasible Learned Acquisition Trajectories for Accelerated MRI
Magnetic Resonance Imaging (MRI) has long been considered to be among the gold standards of today's diagnostic imaging.
Do We Need Depth in State-Of-The-Art Face Authentication?
The raw face stereo images along with the location in the image from which the face is extracted allow the proposed CNN to improve the recognition task while avoiding the need to explicitly handle the geometric structure of the face.
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning
One of the key factors of enabling machine learning models to comprehend and solve real-world tasks is to leverage multimodal data.
Ranked #3 on
Visual Question Answering
on MSRVTT-QA
(Accuracy metric)
Robust Quantization: One Model to Rule Them All
Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed.
MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification
In this work, we propose to employ tools inspired by the Differentiable Neural Architecture Search (D-NAS) literature in order to optimize the architecture for FSL without over-fitting.
Spectral Geometric Matrix Completion
Deep Matrix Factorization (DMF) is an emerging approach to the problem of matrix completion.
Deep geometric matrix completion: Are we doing it right?
We address the problem of reconstructing a matrix from a subset of its entries.
Localization with Limited Annotation for Chest X-rays
We present such a technique for localization with limited annotation, in which the number of images with bounding boxes can be a small fraction of the total dataset (e. g. less than 1%); all other images only possess a whole image label and no bounding box.
Horizontal Flows and Manifold Stochastics in Geometric Deep Learning
We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean.
PILOT: Physics-Informed Learned Optimized Trajectories for Accelerated MRI
Such schemes have already demonstrated substantial effectiveness, leading to considerably shorter acquisition times and improved quality of image reconstruction.
The Shape of Data: Intrinsic Distance for Data Distributions
The ability to represent and compare machine learning models is crucial in order to quantify subtle model changes, evaluate generative models, and gather insights on neural network architectures.
Learning to Detect and Retrieve Objects from Unlabeled Videos
In this work, we propose to exploit the natural correlation in narrations and the visual presence of objects in video, to learn an object detector and retrieval without any manual labeling involved.
Joint learning of cartesian undersampling and reconstruction for accelerated MRI
On the other hand, recent works in optical computational imaging have demonstrated growing success of the simultaneous learning-based design of the acquisition and reconstruction schemes manifesting significant improvement in the reconstruction quality with a constrained time budget.
Self-supervised learning of inverse problem solvers in medical imaging
In light of this, we propose a self-supervised approach to training inverse models in medical imaging in the absence of aligned data.
Learning beamforming in ultrasound imaging
Medical ultrasound (US) is a widespread imaging modality owing its popularity to cost efficiency, portability, speed, and lack of harmful ionizing radiation.
Self-supervised Learning of Dense Shape Correspondence
The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase.
SGR: Self-Supervised Spectral Graph Representation Learning
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand.
NetLSD: Hearing the Shape of a Graph
However, it is a hard task in terms of the expressiveness of the employed similarity measure and the efficiency of its computation.
Social and Information Networks
Deformable Shape Completion with Graph Convolutional Autoencoders
In this work, we propose a novel learning-based method for the completion of partial shapes.
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees.
DIMAL: Deep Isometric Manifold Learning Using Sparse Geodesic Sampling
This paper explores a fully unsupervised deep learning approach for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds.
Efficient Deformable Shape Correspondence via Kernel Matching
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality.
Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.
Cloud Dictionary: Sparse Coding and Modeling for Point Clouds
With the development of range sensors such as LIDAR and time-of-flight cameras, 3D point cloud scans have become ubiquitous in computer vision applications, the most prominent ones being gesture recognition and autonomous driving.
Hamiltonian operator for spectral shape analysis
Many shape analysis methods treat the geometry of an object as a metric space that can be captured by the Laplace-Beltrami operator.
Consistent Discretization and Minimization of the L1 Norm on Manifolds
The L1 norm has been tremendously popular in signal and image processing in the past two decades due to its sparsity-promoting properties.
FPGA system for real-time computational extended depth of field imaging using phase aperture coding
We present a proof-of-concept end-to-end system for computational extended depth of field (EDOF) imaging.
Bayesian Inference of Bijective Non-Rigid Shape Correspondence
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.
Image reconstruction from dense binary pixels
Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital version of the photographic film.
ASIST: Automatic Semantically Invariant Scene Transformation
We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts.
A Picture is Worth a Billion Bits: Real-Time Image Reconstruction from Dense Binary Pixels
In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior.
Random Forests Can Hash
Traditional random forest fails to enforce the consistency of hashes generated from each tree for the same class data, i. e., to preserve the underlying similarity, and it also lacks a principled way for code aggregation across trees.
Graph matching: relax or not?
We consider the problem of exact and inexact matching of weighted undirected graphs, in which a bijective correspondence is sought to minimize a quadratic weight disagreement.
