Marios Savvides

is this you? claim profile

∙ 0 followers
Carnegie Mellon University

Research Professor in ECE, Founder/Director of Carnegie Mellon Biometrics Center at Carnegie Mellon University since 2014, Associate Research Professor & Director of Carnegie Mellon CyLab Biometrics Center at Carnegie Mellon University since 2004, PhD from the Electrical and Computer Engineering also at Carnegie Mellon University, Tapped researchers to form the Office of the Director of National Intelligence (ODNI) 1st Center of Academic Excellence in Science and Technology (CASIS).

Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study

This work aims to empirically clarify a recently discovered perspective ...
04/01/2021 ∙ by Zhiqiang Shen, et al. ∙ 0 ∙ share

read it
Unsupervised Disentanglement of Linear-Encoded Facial Semantics

We propose a method to disentangle linear-encoded facial semantics from ...
03/30/2021 ∙ by Yutong Zheng, et al. ∙ 0 ∙ share

read it
Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due ...
03/02/2021 ∙ by Chenchen Zhu, et al. ∙ 0 ∙ share

read it
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

Previous studies dominantly target at self-supervised learning on real-v...
02/17/2021 ∙ by Zhiqiang Shen, et al. ∙ 0 ∙ share

read it
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning

The goal of few-shot learning is to learn a classifier that can recogniz...
02/08/2021 ∙ by Zhiqiang Shen, et al. ∙ 0 ∙ share

read it
A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection Segmentation

In recent years, deep neural networks have achieved state-of-the-art per...
12/03/2020 ∙ by Ngan Le, et al. ∙ 0 ∙ share

read it
Online Ensemble Model Compression using Knowledge Distillation

This paper presents a novel knowledge distillation based model compressi...
11/15/2020 ∙ by Devesh Walawalkar, et al. ∙ 0 ∙ share

read it
MEAL V2: Boosting Vanilla ResNet-50 to 80 without Tricks

In this paper, we introduce a simple yet effective approach that can boo...
09/17/2020 ∙ by Zhiqiang Shen, et al. ∙ 0 ∙ share

read it
Binarizing MobileNet via Evolution-based Searching

Binary Neural Networks (BNNs), known to be one among the effectively com...
05/13/2020 ∙ by Hai Phan, et al. ∙ 0 ∙ share

read it
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification

Convolutional neural networks (CNN) are capable of learning robust repre...
03/29/2020 ∙ by Devesh Walawalkar, et al. ∙ 0 ∙ share

read it
Rethinking Image Mixture for Unsupervised Visual Representation Learning

In supervised learning, smoothing label/prediction distribution in neura...
03/11/2020 ∙ by Zhiqiang Shen, et al. ∙ 8 ∙ share

read it
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

In this paper, we propose several ideas for enhancing a binary network t...
03/07/2020 ∙ by Zechun Liu, et al. ∙ 0 ∙ share

read it
Solving Missing-Annotation Object Detection with Background Recalibration Loss

This paper focuses on a novel and challenging detection scenario: A majo...
02/12/2020 ∙ by Han Zhang, et al. ∙ 0 ∙ share

read it
Soft Anchor-Point Object Detection

Recently, anchor-free detectors have shown great potential to outperform...
11/27/2019 ∙ by Chenchen Zhu, et al. ∙ 0 ∙ share

read it
Towards a Hypothesis on Visual Transformation based Self-Supervision

We propose the first qualitative hypothesis characterizing the behavior ...
11/24/2019 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
Learning Non-Parametric Invariances from Data with Permanent Random Connectomes

One of the fundamental problems in supervised classification and in mach...
11/13/2019 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses

Unsupervised domain adaptive object detection aims to learn a robust det...
11/06/2019 ∙ by Zhiqiang Shen, et al. ∙ 24 ∙ share

read it
Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement

Generic Image recognition is a fundamental and fairly important visual p...
08/22/2019 ∙ by Zhiqiang Shen, et al. ∙ 24 ∙ share

read it
MoBiNet: A Mobile Binary Network for Image Classification

MobileNet and Binary Neural Networks are two among the most widely used ...
07/29/2019 ∙ by Hai Phan, et al. ∙ 2 ∙ share

read it
Proximal Splitting Networks for Image Restoration

Image restoration problems are typically ill-posed requiring the design ...
03/17/2019 ∙ by Raied Aljadaany, et al. ∙ 0 ∙ share

read it
Feature Selective Anchor-Free Module for Single-Shot Object Detection

We motivate and present feature selective anchor-free (FSAF) module, a s...
03/02/2019 ∙ by Chenchen Zhu, et al. ∙ 0 ∙ share

read it
RankGAN: A Maximum Margin Ranking GAN for Generating Faces

We present a new stage-wise learning paradigm for training generative ad...
12/19/2018 ∙ by Rahul Dey, et al. ∙ 12 ∙ share

read it
Deep Recurrent Level Set for Segmenting Brain Tumors

Variational Level Set (VLS) has been a widely used method in medical seg...
10/10/2018 ∙ by T. Hoang Ngan Le, et al. ∙ 0 ∙ share

read it
Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection

Non-maximum suppression (NMS) is essential for state-of-the-art object d...
09/23/2018 ∙ by Yihui He, et al. ∙ 0 ∙ share

read it
Perturbative Neural Networks

Convolutional neural networks are witnessing wide adoption in computer v...
06/05/2018 ∙ by Felix Juefei-Xu, et al. ∙ 2 ∙ share

read it
Ring loss: Convex Feature Normalization for Face Recognition

We motivate and present Ring loss, a simple and elegant feature normaliz...
02/28/2018 ∙ by Yutong Zheng, et al. ∙ 1 ∙ share

read it
Seeing Small Faces from Robust Anchor's Perspective

This paper introduces a novel anchor design to support anchor-based face...
02/25/2018 ∙ by Chenchen Zhu, et al. ∙ 0 ∙ share

read it
Non-Parametric Transformation Networks

ConvNets have been very effective in many applications where it is requi...
01/14/2018 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

This paper presents a novel Generative Probabilistic Modeling under an I...
11/28/2017 ∙ by Chi Nhan Duong, et al. ∙ 0 ∙ share

read it
Class Correlation affects Single Object Localization using Pre-trained ConvNets

The problem of object localization has become one of the mainstream prob...
10/26/2017 ∙ by Pokkalla Harsha Vardhan, et al. ∙ 0 ∙ share

read it
Max-Margin Invariant Features from Transformed Unlabeled Data

The study of representations invariant to common transformations of the ...
10/24/2017 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses

Facial alignment involves finding a set of landmark points on an image w...
07/18/2017 ∙ by Chandrasekhar Bhagavatula, et al. ∙ 0 ∙ share

read it
Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition

Modeling the long-term facial aging process is extremely challenging due...
03/24/2017 ∙ by Chi Nhan Duong, et al. ∙ 0 ∙ share

read it
How ConvNets model Non-linear Transformations

In this paper, we theoretically address three fundamental problems invol...
02/24/2017 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
Emergence of Selective Invariance in Hierarchical Feed Forward Networks

Many theories have emerged which investigate how in- variance is generat...
01/30/2017 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it
Towards a Deep Learning Framework for Unconstrained Face Detection

Robust face detection is one of the most important pre-processing steps ...
12/16/2016 ∙ by Yutong Zheng, et al. ∙ 0 ∙ share

read it
Local Binary Convolutional Neural Networks

We propose local binary convolution (LBC), an efficient alternative to c...
08/22/2016 ∙ by Felix Juefei-Xu, et al. ∙ 0 ∙ share

read it
CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection

Robust face detection in the wild is one of the ultimate components to s...
06/17/2016 ∙ by Chenchen Zhu, et al. ∙ 0 ∙ share

read it
Unitary-Group Invariant Kernels and Features from Transformed Unlabeled Data

The study of representations invariant to common transformations of the ...
11/18/2015 ∙ by Dipan K. Pal, et al. ∙ 0 ∙ share

read it

Marios Savvides

Featured Co-authors