Search Results for author:
Found 16 papers, 5 papers with code
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training
Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples.
Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation
Accurately estimating the pose of an object is a crucial task in computer vision and robotics.
Understanding the Feature Norm for Out-of-Distribution Detection
(3) The conventional feature norm fails to capture the deactivation tendency of hidden layer neurons, which may lead to misidentification of ID samples as OOD instances.
Nearest Neighbor Guidance for Out-of-Distribution Detection
Detecting out-of-distribution (OOD) samples are crucial for machine learning models deployed in open-world environments.
Ranked #1 on
Out-of-Distribution Detection
on ImageNet-1k vs Curated OODs (avg.)
(using extra training data)
Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service
In this paper we show hyperdimensional computing can be a rescue for privacy-preserving machine learning over encrypted data.
Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation
Very low-resolution face recognition (VLRFR) poses unique challenges, such as tiny regions of interest and poor resolution due to extreme standoff distance or wide viewing angle of the acquisition devices.
Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning
In this paper, we focus on addressing the open-set face identification problem on a few-shot gallery by fine-tuning.
Understanding Open-Set Recognition by Jacobian Norm and Inter-Class Separation
Overall, the discrepancy in the Jacobian norm between the known and unknown classes enables OSR.
Customs Import Declaration Datasets
Given the huge volume of cross-border flows, effective and efficient control of trade becomes more crucial in protecting people and society from illicit trade.
DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation
Our pose estimation method, dynamic projective spatial transformer network (DProST), localizes the region of interest grid on the rays in camera space and transforms the grid to object space by estimated pose.
CSQ: Centered Symmetric Quantization for Extremely Low Bit Neural Networks
We show that this asymmetry in the number of positive and negative quantization levels can result in significant quantization error and performance degradation at low precision.
Periocular Embedding Learning with Consistent Knowledge Distillation from Face
Overall, CKD empowers the sole periocular network to produce robust discriminative embeddings for periocular recognition in the wild.
Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
In DCAE, (a) we force a compact latent space to bijectively represent the in-class data by reconstructing them through internal discriminative layers of generative adversarial nets.
On the Risk of Cancelable Biometrics
Cancelable biometrics (CB) employs an irreversible transformation to convert the biometric features into transformed templates while preserving the relative distance between two templates for security and privacy protection.
PuVAE: A Variational Autoencoder to Purify Adversarial Examples
Deep neural networks are widely used and exhibit excellent performance in many areas.
Ranked #2 on
Adversarial Defense against FGSM Attack
on MNIST
Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification
Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification.
