research
∙
08/21/2023
Spurious Correlations and Where to Find Them
Spurious correlations occur when a model learns unreliable features from...
share
research
∙
08/12/2023
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
Deploying high-performance convolutional neural network (CNN) models on ...
research
∙
08/03/2023
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Multi-task learning (MTL) seeks to learn a single model to accomplish mu...
research
∙
08/03/2023
On the Biometric Capacity of Generative Face Models
There has been tremendous progress in generating realistic faces with hi...
research
∙
07/31/2023
Discovering Adaptable Symbolic Algorithms from Scratch
Autonomous robots deployed in the real world will need control policies ...
research
∙
06/22/2023
On Hate Scaling Laws For Data-Swamps
`Scale the model, scale the data, scale the GPU-farms' is the reigning s...
research
∙
02/15/2023
TFormer: A Transmission-Friendly ViT Model for IoT Devices
Deploying high-performance vision transformer (ViT) models on ubiquitous...
research
∙
12/21/2022
Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective
Efforts to improve the adversarial robustness of convolutional neural ne...
research
∙
12/19/2022
Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components
Structural components are typically exposed to dynamic loading, such as ...
research
∙
11/28/2022
Physics Informed Neural Network for Dynamic Stress Prediction
Structural failures are often caused by catastrophic events such as eart...
research
∙
08/26/2022
NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems
Structural monitoring for complex built environments often suffers from ...
research
∙
08/15/2022
HEFT: Homomorphically Encrypted Fusion of Biometric Templates
This paper proposes a non-interactive end-to-end solution for secure fus...
research
∙
07/20/2022
Towards Transmission-Friendly and Robust CNN Models over Cloud and Device
Deploying deep convolutional neural network (CNN) models on ubiquitous I...
research
∙
04/02/2022
Do learned representations respect causal relationships?
Data often has many semantic attributes that are causally associated wit...
research
∙
12/01/2021
Generating Diverse 3D Reconstructions from a Single Occluded Face Image
Occlusions are a common occurrence in unconstrained face images. Single ...
research
∙
09/12/2021
Adversarial Representation Learning With Closed-Form Solvers
Adversarial representation learning aims to learn data representations f...
research
∙
08/19/2021
Spatially-Adaptive Image Restoration using Distortion-Guided Networks
We present a general learning-based solution for restoring images suffer...
research
∙
07/20/2020
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
In this paper, we propose an efficient NAS algorithm for generating task...
research
∙
05/12/2020
Neural Architecture Transfer
Neural architecture search (NAS) has emerged as a promising avenue for a...
research
∙
03/31/2020
MUXConv: Information Multiplexing in Convolutional Neural Networks
Convolutional neural networks have witnessed remarkable improvements in ...
research
∙
03/27/2020
HERS: Homomorphically Encrypted Representation Search
We present a method to search for a probe (or query) image representatio...
research
∙
12/03/2019
Multi-Criterion Evolutionary Design of Deep Convolutional Neural Networks
Convolutional neural networks (CNNs) are the backbones of deep learning ...
research
∙
10/16/2019
On the Global Optima of Kernelized Adversarial Representation Learning
Adversarial representation learning is a promising paradigm for obtainin...
research
∙
04/11/2019
Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach
Image recognition systems have demonstrated tremendous progress over the...
research
∙
12/19/2018
RankGAN: A Maximum Margin Ranking GAN for Generating Faces
We present a new stage-wise learning paradigm for training generative ad...
research
∙
06/05/2018
Perturbative Neural Networks
Convolutional neural networks are witnessing wide adoption in computer v...
research
∙
05/01/2018
Secure Face Matching Using Fully Homomorphic Encryption
Face recognition technology has demonstrated tremendous progress over th...
research
∙
03/26/2018
On the Intrinsic Dimensionality of Face Representation
The two underlying factors that determine the efficacy of face represent...
research
∙
10/06/2017
Efficient K-Shot Learning with Regularized Deep Networks
Feature representations from pre-trained deep neural networks have been ...
research
∙
09/29/2017
On the Capacity of Face Representation
Face recognition is a widely used technology with numerous large-scale a...
research
∙
07/19/2017
Face Alignment Robust to Pose, Expressions and Occlusions
We propose an Ensemble of Robust Constrained Local Models for alignment ...
research
∙
04/07/2017
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
We propose a privacy-preserving framework for learning visual classifier...
research
∙
12/15/2016
Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
We introduce the concept of a Visual Compiler that generates a scene spe...
research
∙
12/09/2016
Gesture-based Bootstrapping for Egocentric Hand Segmentation
Accurately identifying hands in images is a key sub-task for human activ...
research
∙
08/22/2016
Local Binary Convolutional Neural Networks
We propose local binary convolution (LBC), an efficient alternative to c...
research
∙
11/10/2014
Zero-Aliasing Correlation Filters for Object Recognition
Correlation filters (CFs) are a class of classifiers that are attractive...
research
∙
04/24/2014