Search Results for author:
Found 44 papers, 20 papers with code
Correlation Filters for Object Alignment
A typical object alignment system consists of a landmark appearance model which is used to obtain an initial shape and a shape model which refines this initial shape by correcting the initialization errors.
Maximum Margin Vector Correlation Filter
Correlation Filters (CFs) are a class of classifiers which are designed for accurate pattern localization.
Zero-Aliasing Correlation Filters for Object Recognition
However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain.
Learning Scene-Specific Pedestrian Detectors Without Real Data
Our results also yield a surprising result, that our method using purely synthetic data is able to outperform models trained on real scene-specific data when data is limited.
Local Binary Convolutional Neural Networks
We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN).
Gesture-based Bootstrapping for Egocentric Hand Segmentation
Concretely, our approach uses two convolutional neural networks: (1) a gesture network that uses pre-defined motion information to detect the hand region; and (2) an appearance network that learns a person specific model of the hand region based on the output of the gesture network.
Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data.
Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
A recent advance called the WGAN based on Wasserstein distance can improve on the KL and JS-divergence based GANs, and alleviate the gradient vanishing, instability, and mode collapse issues that are common in the GAN training.
Face Alignment Robust to Pose, Expressions and Occlusions
To account for partial occlusions we introduce, Robust Constrained Local Models, that comprises of a deformable shape and local landmark appearance model and reasons over binary occlusion labels.
On the Capacity of Face Representation
Numerical experiments on unconstrained faces (IJB-C) provides a capacity upper bound of $2. 7\times10^4$ for FaceNet and $8. 4\times10^4$ for SphereFace representation at a false acceptance rate (FAR) of 1%.
Efficient K-Shot Learning with Regularized Deep Networks
To efficiently search for optimal groupings conditioned on the input data, we propose a reinforcement learning search strategy using recurrent networks to learn the optimal group assignments for each network layer.
On the Intrinsic Dimensionality of Image Representations
This paper addresses the following questions pertaining to the intrinsic dimensionality of any given image representation: (i) estimate its intrinsic dimensionality, (ii) develop a deep neural network based non-linear mapping, dubbed DeepMDS, that transforms the ambient representation to the minimal intrinsic space, and (iii) validate the veracity of the mapping through image matching in the intrinsic space.
Secure Face Matching Using Fully Homomorphic Encryption
In this paper, we explore the practicality of using a fully homomorphic encryption based framework to secure a database of face templates.
Perturbative Neural Networks
Convolutional neural networks are witnessing wide adoption in computer vision systems with numerous applications across a range of visual recognition tasks.
RankGAN: A Maximum Margin Ranking GAN for Generating Faces
We present a new stage-wise learning paradigm for training generative adversarial networks (GANs).
Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach
Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images.
On the Global Optima of Kernelized Adversarial Representation Learning
Numerical experiments on UCI, Extended Yale B and CIFAR-100 datasets indicate that, (a) practically, our solution is ideal for "imparting" provable invariance to any biased pre-trained data representation, and (b) empirically, the trade-off between utility and invariance provided by our solution is comparable to iterative minimax optimization of existing deep neural network based approaches.
Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches.
Ranked #1 on
Pneumonia Detection
on ChestX-ray14
HERS: Homomorphically Encrypted Representation Search
We present a method to search for a probe (or query) image representation against a large gallery in the encrypted domain.
MUXConv: Information Multiplexing in Convolutional Neural Networks
To overcome this limitation, we present MUXConv, a layer that is designed to increase the flow of information by progressively multiplexing channel and spatial information in the network, while mitigating computational complexity.
Ranked #4 on
Pneumonia Detection
on ChestX-ray14
Neural Architecture Transfer
At the same time, the architecture search and transfer is orders of magnitude more efficient than existing NAS methods.
Ranked #1 on
Neural Architecture Search
on STL-10
Fine-Grained Image Classification
Neural Architecture Search
+1
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives.
Ranked #17 on
Neural Architecture Search
on ImageNet
Spatially-Adaptive Image Restoration using Distortion-Guided Networks
However, we hypothesize that such spatially rigid processing is suboptimal for simultaneously restoring the degraded pixels as well as reconstructing the clean regions of the image.
Adversarial Representation Learning With Closed-Form Solvers
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time.
Generating Diverse 3D Reconstructions from a Single Occluded Face Image
Furthermore, while a plurality of 3D reconstructions is plausible in the occluded regions, existing approaches are limited to generating only a single solution.
Do learned representations respect causal relationships?
Second, we apply NCINet to identify the causal relations between image representations of different pairs of attributes with known and unknown causal relations between the labels.
HEFT: Homomorphically Encrypted Fusion of Biometric Templates
This paper proposes a non-interactive end-to-end solution for secure fusion and matching of biometric templates using fully homomorphic encryption (FHE).
NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems
Structural monitoring for complex built environments often suffers from mismatch between design, laboratory testing, and actual built parameters.
Physics Informed Neural Network for Dynamic Stress Prediction
Therefore, to reduce computational cost while maintaining accuracy, a Physics Informed Neural Network (PINN), PINN-Stress model, is proposed to predict the entire sequence of stress distribution based on Finite Element simulations using a partial differential equation (PDE) solver.
Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components
Therefore, to reduce computational cost while preserving accuracy, a deep learning model, Neuro-DynaStress, is proposed to predict the entire sequence of stress distribution based on finite element simulations using a partial differential equation (PDE) solver.
Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective
In contrast, little attention was devoted to analyzing the role of architectural elements (such as topology, depth, and width) on adversarial robustness.
ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding
We present ProTeGe as the first method to perform VTG-based untrimmed pretraining to bridge the gap between trimmed pretrained backbones and downstream VTG tasks.
Revisiting Residual Networks for Adversarial Robustness
Then we design a robust residual block, dubbed RobustResBlock, and a compound scaling rule, dubbed RobustScaling, to distribute depth and width at the desired FLOP count.
TFormer: A Transmission-Friendly ViT Model for IoT Devices
The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN).
Discovering Adaptable Symbolic Algorithms from Scratch
We evolve modular policies that tune their model parameters and alter their inference algorithm on-the-fly to adapt to sudden environmental changes.
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Our key idea is to employ non-learnable primitives to extract a diverse set of task-agnostic features and recombine them into a shared branch common to all tasks and explicit task-specific branches reserved for each task.
On the Biometric Capacity of Generative Face Models
Our capacity estimates indicate that (a) under ArcFace representation at a false acceptance rate (FAR) of 0. 1%, StyleGAN3 and DCFace have a capacity upper bound of $1. 43\times10^6$ and $1. 190\times10^4$, respectively; (b) the capacity reduces drastically as we lower the desired FAR with an estimate of $1. 796\times10^4$ and $562$ at FAR of 1% and 10%, respectively, for StyleGAN3; (c) there is no discernible disparity in the capacity w. r. t gender; and (d) for some generative models, there is an appreciable disparity in the capacity w. r. t age.
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models.
Spurious Correlations and Where to Find Them
Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning.
AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE
Lastly, AutoFHE accelerates inference and improves accuracy by $103\times$ and 3. 46%, respectively, compared to CNNs under TFHE.
Mechanics-Informed Autoencoder Enables Automated Detection and Localization of Unforeseen Structural Damage
Structural health monitoring (SHM) is vital for ensuring the safety and longevity of structures like buildings and bridges.
FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
However, owing to the nature of their training process, these models have the potential to 1) propagate or amplify societal biases in the training data and 2) learn to rely on spurious features.
Utility-Fairness Trade-Offs and How to Find Them
and 2) How can we numerically quantify these trade-offs from data for a desired prediction task and demographic attribute of interest?
