Search Results for author:
Found 42 papers, 12 papers with code
On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions
In this paper, we relax the requirement of having a central machine for the target subset by proposing a novel distributed bounding algorithm with provable approximation guarantees.
Simulated Overparameterization
Building upon this framework, we present a novel, architecture agnostic algorithm called "majority kernels", which seamlessly integrates with predominant architectures, including Transformer models.
A Weighted K-Center Algorithm for Data Subset Selection
The success of deep learning hinges on enormous data and large models, which require labor-intensive annotations and heavy computation costs.
Rethinking FID: Towards a Better Evaluation Metric for Image Generation
It is an unbiased estimator that does not make any assumptions on the probability distribution of the embeddings and is sample efficient.
MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts.
Leveraging Importance Weights in Subset Selection
In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i. e. further train model weights) once a large enough batch of examples is selected.
When does mixup promote local linearity in learned representations?
Towards this, we study two questions: (1) how does the Mixup loss that enforces linearity in the \emph{last} network layer propagate the linearity to the \emph{earlier} layers?
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
We propose a tractable heuristic for solving the combinatorial extension of OBS, in which we select weights for simultaneous removal, as well as a systematic update of the remaining weights.
Approximate Bijective Correspondence for isolating factors of variation
We propose a novel algorithm that relies on a weak form of supervision where the data is partitioned into sets according to certain \textit{inactive} factors of variation.
Model-Efficient Deep Learning with Kernelized Classification
We investigate the possibility of using the embeddings produced by a lightweight network more effectively with a nonlinear classification layer.
Less data is more: Selecting informative and diverse subsets with balancing constraints
Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost.
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
Single image pose estimation is a fundamental problem in many vision and robotics tasks, and existing deep learning approaches suffer by not completely modeling and handling: i) uncertainty about the predictions, and ii) symmetric objects with multiple (sometimes infinite) correct poses.
Balancing Robustness and Sensitivity using Feature Contrastive Learning
It is generally believed that robust training of extremely large networks is critical to their success in real-world applications.
Less is more: Selecting informative and diverse subsets with balancing constraints
Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost.
Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision
We propose a novel algorithm that utilizes a weak form of supervision where the data is partitioned into sets according to certain inactive (common) factors of variation which are invariant across elements of each set.
Scaling Up Exact Neural Network Compression by ReLU Stability
We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable.
Leveraging affinity cycle consistency to isolate factors of variation in learned representations
In this work, we operate in the setting where limited information is known about the data in the form of groupings, or set membership, and the task is to learn representations which isolate the factors of variation that are common across the groupings.
Kernelized Classification in Deep Networks
We propose a kernelized classification layer for deep networks.
Mapping of Sparse 3D Data using Alternating Projection
We propose a novel technique to register sparse 3D scans in the absence of texture.
Lossless Compression of Deep Neural Networks
Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy.
Can generalised relative pose estimation solve sparse 3D registration?
In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans.
Equivalent and Approximate Transformations of Deep Neural Networks
On the practical side, we show that certain rectified linear units (ReLUs) can be safely removed from a network if they are always active or inactive for any valid input.
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment
3D scan registration is a classical, yet a highly useful problem in the context of 3D sensors such as Kinect and Velodyne.
3DRegNet: A Deep Neural Network for 3D Point Registration
Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame.
Empirical Bounds on Linear Regions of Deep Rectifier Networks
Our first contribution is a method to sample the activation patterns defined by ReLUs using universal hash functions.
Novel Single View Constraints for Manhattan 3D Line Reconstruction
We treat the line segments in the image to be part of a graph similar to straws and connectors game, where the goal is to back-project the line segments in 3D space and while ensuring that some of these 3D line segments connect with each other (i. e., truly intersect in 3D space) to form the 3D structure.
Simultaneous Edge Alignment and Learning
Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications.
A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines
We show that the solution for the case of two points and one line can be formulated as a fourth degree equation.
VLASE: Vehicle Localization by Aggregating Semantic Edges
In this paper, we propose VLASE, a framework to use semantic edge features from images to achieve on-road localization.
How Could Polyhedral Theory Harness Deep Learning?
The holy grail of deep learning is to come up with an automatic method to design optimal architectures for different applications.
Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
Vanishing points and vanishing lines are classical geometrical concepts in perspective cameras that have a lineage dating back to 3 centuries.
Learning Strict Identity Mappings in Deep Residual Networks
A family of super deep networks, referred to as residual networks or ResNet, achieved record-beating performance in various visual tasks such as image recognition, object detection, and semantic segmentation.
Class Subset Selection for Transfer Learning using Submodularity
To accomplish this, we use a submodular set function to model the accuracy achievable on a new task when the features have been learned on a given subset of classes of the source dataset.
Bounding and Counting Linear Regions of Deep Neural Networks
We investigate the complexity of deep neural networks (DNN) that represent piecewise linear (PWL) functions.
Submodular Function Maximization for Group Elevator Scheduling
We show that this objective function is submodular.
CASENet: Deep Category-Aware Semantic Edge Detection
To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features.
Ranked #1 on
Edge Detection
on Cityscapes test
High-Performance and Tunable Stereo Reconstruction
Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance.
Layered Interpretation of Street View Images
We propose a layered street view model to encode both depth and semantic information on street view images for autonomous driving.
Line-Sweep: Cross-Ratio For Wide-Baseline Matching and 3D Reconstruction
We propose a simple and useful idea based on cross-ratio constraint for wide-baseline matching and 3D reconstruction.
Single Image Calibration of Multi-axial Imaging Systems
We describe such setups as multi-axial imaging systems, since a single sphere results in an axial system.
Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes
In this paper, we consider the problem of detecting junctions and using them for recovering the spatial layout of an indoor scene.
Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions
E +n^4 {\log}^{O(1)} n)$ where $E$ is the time required to evaluate the function and $n$ is the number of variables \cite{Lee2015}.
