Search Results for author: Marios Savvides

Found 60 papers, 22 papers with code

Fairness in Visual Clustering: A Novel Transformer Clustering Approach

no code implementations14 Apr 2023 Xuan-Bac Nguyen, Chi Nhan Duong, Marios Savvides, Kaushik Roy, Hugh Churchill, Khoa Luu

Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal.

Attribute Clustering +2

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

4 code implementations26 Jan 2023 Hao Chen, Ran Tao, Yue Fan, Yidong Wang, Jindong Wang, Bernt Schiele, Xing Xie, Bhiksha Raj, Marios Savvides

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance.

imbalanced classification

Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization

no code implementations CVPR 2023 Ran Tao, Hao Chen, Marios Savvides

This observation further motivates us to propose the Transductive Fine-tuning with Margin-based uncertainty weighting and Probability regularization (TF-MP), which learns a more balanced class marginal distribution.

Few-Shot Learning

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

2 code implementations CVPR 2023 Fangyi Chen, Han Zhang, Kai Hu, Yu-Kai Huang, Chenchen Zhu, Marios Savvides

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage.

Attribute Object +2

An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning

no code implementations20 Nov 2022 Hao Chen, Yue Fan, Yidong Wang, Jindong Wang, Bernt Schiele, Xing Xie, Marios Savvides, Bhiksha Raj

While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data.

Pseudo Label

Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

no code implementations11 Sep 2022 Thanh-Dat Truong, Chi Nhan Duong, Ngan Le, Marios Savvides, Khoa Luu

We therefore introduce a new method named Attention-based Bijective Generative Adversarial Networks in a Distillation framework (DAB-GAN) to synthesize faces of a subject given his/her extracted face recognition features.

Face Recognition Face Reconstruction +2

Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets

no code implementations15 Aug 2022 Hao Chen, Ran Tao, Han Zhang, Yidong Wang, Wei Ye, Jindong Wang, Guosheng Hu, Marios Savvides

Beyond classification, Conv-Adapter can generalize to detection and segmentation tasks with more than 50% reduction of parameters but comparable performance to the traditional full fine-tuning.

Transfer Learning

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

4 code implementations15 May 2022 Yidong Wang, Hao Chen, Qiang Heng, Wenxin Hou, Yue Fan, Zhen Wu, Jindong Wang, Marios Savvides, Takahiro Shinozaki, Bhiksha Raj, Bernt Schiele, Xing Xie

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization.

Fairness Semi-Supervised Image Classification

Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling

no code implementations7 Apr 2022 Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides

Class-agnostic bias is defined as the distribution shifting introduced by domain difference, which we propose Distribution Calibration Module(DCM) to reduce.

Few-Shot Learning

Unitail: Detecting, Reading, and Matching in Retail Scene

no code implementations1 Apr 2022 Fangyi Chen, Han Zhang, Zaiwang Li, Jiachen Dou, Shentong Mo, Hao Chen, Yongxin Zhang, Uzair Ahmed, Chenchen Zhu, Marios Savvides

To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene.

Benchmarking Dense Object Detection +2

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

no code implementations25 Aug 2021 Ngan Le, Vidhiwar Singh Rathour, Kashu Yamazaki, Khoa Luu, Marios Savvides

In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision.

Image Segmentation object-detection +5

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

no code implementations CVPR 2021 Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Zhiqiang Shen, Marios Savvides

In this work, we investigate utilizing this semantic relation together with the visual information and introduce explicit relation reasoning into the learning of novel object detection.

Few-Shot Object Detection Novel Object Detection +2

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

1 code implementation CVPR 2021 Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, Marios Savvides

In this paper, we focus on this more difficult scenario: learning networks where both weights and activations are binary, meanwhile, without any human annotated labels.

Contrastive Learning Self-Supervised Learning

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

no code implementations8 Feb 2021 Zhiqiang Shen, Zechun Liu, Jie Qin, Marios Savvides, Kwang-Ting Cheng

A common practice for this task is to train a model on the base set first and then transfer to novel classes through fine-tuning (Here fine-tuning procedure is defined as transferring knowledge from base to novel data, i. e. learning to transfer in few-shot scenario.)

Few-Shot Learning

Improve Novel Class Generalization By Adaptive Feature Distribution for Few-Shot Learning

no code implementations1 Jan 2021 Ran Tao, Marios Savvides

By addressing the difference between feature distributions of base and novel classes, we propose the adaptive feature distribution method which is to finetune one scale vector using the support set of novel classes.

Few-Shot Learning

Contrast and Order Representations for Video Self-Supervised Learning

no code implementations ICCV 2021 Kai Hu, Jie Shao, YuAn Liu, Bhiksha Raj, Marios Savvides, Zhiqiang Shen

To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.

Action Recognition Self-Supervised Learning

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

no code implementations3 Dec 2020 Ngan Le, Kashu Yamazaki, Dat Truong, Kha Gia Quach, Marios Savvides

The first objective is performed by our proposed contextual brain tumor detection network, which plays a role of an attention gate and focuses on the region around brain tumor only while ignoring the far neighbor background which is less correlated to the tumor.

Brain Tumor Segmentation Tumor Segmentation

Online Ensemble Model Compression using Knowledge Distillation

1 code implementation ECCV 2020 Devesh Walawalkar, Zhiqiang Shen, Marios Savvides

This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble.

Knowledge Distillation Model Compression

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks

1 code implementation17 Sep 2020 Zhiqiang Shen, Marios Savvides

Our result can be regarded as a strong baseline using knowledge distillation, and to our best knowledge, this is also the first method that is able to boost vanilla ResNet-50 to surpass 80% on ImageNet without architecture modification or additional training data.

Image Classification Knowledge Distillation

Binarizing MobileNet via Evolution-based Searching

no code implementations CVPR 2020 Hai Phan, Zechun Liu, Dang Huynh, Marios Savvides, Kwang-Ting Cheng, Zhiqiang Shen

Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs), assuming an approximately optimal trade-off between computational cost and model accuracy.

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

3 code implementations ECCV 2020 Zechun Liu, Zhiqiang Shen, Marios Savvides, Kwang-Ting Cheng

In this paper, we propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost.

Solving Missing-Annotation Object Detection with Background Recalibration Loss

2 code implementations12 Feb 2020 Han Zhang, Fangyi Chen, Zhiqiang Shen, Qiqi Hao, Chenchen Zhu, Marios Savvides

In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image.

Object object-detection +1

Soft Anchor-Point Object Detection

2 code implementations ECCV 2020 Chenchen Zhu, Fangyi Chen, Zhiqiang Shen, Marios Savvides

In this work, we boost the performance of the anchor-point detector over the key-point counterparts while maintaining the speed advantage.

Dense Object Detection feature selection +2

Towards a Hypothesis on Visual Transformation based Self-Supervision

no code implementations24 Nov 2019 Dipan K. Pal, Sreena Nallamothu, Marios Savvides

Overall, this paper aims to shed light on the phenomenon of visual transformation based self-supervision.


Learning Non-Parametric Invariances from Data with Permanent Random Connectomes

no code implementations13 Nov 2019 Dipan K. Pal, Akshay Chawla, Marios Savvides

One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data.

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

1 code implementation6 Nov 2019 Zhiqiang Shen, Harsh Maheshwari, Weichen Yao, Marios Savvides

Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different.

object-detection Object Detection

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

no code implementations22 Aug 2019 Zhiqiang Shen, Zhankui He, Wanyun Cui, Jiahui Yu, Yutong Zheng, Chenchen Zhu, Marios Savvides

In order to distill diverse knowledge from different trained (teacher) models, we propose to use adversarial-based learning strategy where we define a block-wise training loss to guide and optimize the predefined student network to recover the knowledge in teacher models, and to promote the discriminator network to distinguish teacher vs. student features simultaneously.

Knowledge Distillation

MoBiNet: A Mobile Binary Network for Image Classification

no code implementations29 Jul 2019 Hai Phan, Dang Huynh, Yihui He, Marios Savvides, Zhiqiang Shen

MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platforms. In this paper, we present a simple yet efficient scheme to exploit MobileNet binarization at activation function and model weights.

Binarization Classification +2

Proximal Splitting Networks for Image Restoration

no code implementations17 Mar 2019 Raied Aljadaany, Dipan K. Pal, Marios Savvides

This is in contrast to the common practice in literature of having the prior to be fixed and fully instantiated even during training stages.

Image Denoising Image Restoration +1

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

4 code implementations CVPR 2019 Chenchen Zhu, Yihui He, Marios Savvides

The general concept of the FSAF module is online feature selection applied to the training of multi-level anchor-free branches.

feature selection object-detection +1

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

1 code implementation19 Dec 2018 Rahul Dey, Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

We present a new stage-wise learning paradigm for training generative adversarial networks (GANs).

Face Generation

Deep Recurrent Level Set for Segmenting Brain Tumors

no code implementations10 Oct 2018 T. Hoang Ngan Le, Raajitha Gummadi, Marios Savvides

In each step, the Convolutional Layer is fed with the LevelSet map to obtain a brain tumor feature map.

Brain Tumor Segmentation Segmentation +1

Perturbative Neural Networks

3 code implementations CVPR 2018 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

Convolutional neural networks are witnessing wide adoption in computer vision systems with numerous applications across a range of visual recognition tasks.

Ring loss: Convex Feature Normalization for Face Recognition

no code implementations CVPR 2018 Yutong Zheng, Dipan K. Pal, Marios Savvides

We motivate and present Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax.

Face Identification Face Recognition +1

Seeing Small Faces from Robust Anchor's Perspective

no code implementations CVPR 2018 Chenchen Zhu, Ran Tao, Khoa Luu, Marios Savvides

This paper introduces a novel anchor design to support anchor-based face detection for superior scale-invariant performance, especially on tiny faces.

Face Detection

Non-Parametric Transformation Networks

no code implementations14 Jan 2018 Dipan K. Pal, Marios Savvides

In this paper, we introduce a new class of deep convolutional architectures called Non-Parametric Transformation Networks (NPTNs) which can learn \textit{general} invariances and symmetries directly from data.


Improving Object Detection from Scratch via Gated Feature Reuse

2 code implementations4 Dec 2017 Zhiqiang Shen, Honghui Shi, Jiahui Yu, Hai Phan, Rogerio Feris, Liangliang Cao, Ding Liu, Xinchao Wang, Thomas Huang, Marios Savvides

In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i. e., without pre-trained models).

Object object-detection +1

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

no code implementations ICCV 2017 Chandrasekhar Bhagavatula, Chenchen Zhu, Khoa Luu, Marios Savvides

We present our novel approach to simultaneously extract the 3D shape of the face and the semantically consistent 2D alignment through a 3D Spatial Transformer Network (3DSTN) to model both the camera projection matrix and the warping parameters of a 3D model.

Face Alignment

Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking

1 code implementation17 Apr 2017 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

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.

Deep Contextual Recurrent Residual Networks for Scene Labeling

no code implementations12 Apr 2017 T. Hoang Ngan Le, Chi Nhan Duong, Ligong Han, Khoa Luu, Marios Savvides, Dipan Pal

Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems.

Representation Learning Scene Labeling

Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation

1 code implementation12 Apr 2017 Ngan Le, Kha Gia Quach, Khoa Luu, Marios Savvides, Chenchen Zhu

To address these issues and boost the classic variational LS methods to a new level of the learnable deep learning approaches, we propose a novel definition of contour evolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under the energy minimization of a variational LS functional.

Segmentation Semantic Segmentation

How ConvNets model Non-linear Transformations

no code implementations24 Feb 2017 Dipan K. Pal, Marios Savvides

In this paper, we theoretically address three fundamental problems involving deep convolutional networks regarding invariance, depth and hierarchy.

Emergence of Selective Invariance in Hierarchical Feed Forward Networks

no code implementations30 Jan 2017 Dipan K. Pal, Vishnu Boddeti, Marios Savvides

We illustrate the general notion of selective invari- ance through object categorization experiments on large- scale datasets such as SVHN and ILSVRC 2012.

Object Categorization

Towards a Deep Learning Framework for Unconstrained Face Detection

no code implementations16 Dec 2016 Yutong Zheng, Chenchen Zhu, Khoa Luu, Chandrasekhar Bhagavatula, T. Hoang Ngan Le, Marios Savvides

Robust face detection is one of the most important pre-processing steps to support facial expression analysis, facial landmarking, face recognition, pose estimation, building of 3D facial models, etc.

Face Detection Face Recognition +2

Local Binary Convolutional Neural Networks

7 code implementations CVPR 2017 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN).

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

no code implementations17 Jun 2016 Chenchen Zhu, Yutong Zheng, Khoa Luu, Marios Savvides

Robust face detection in the wild is one of the ultimate components to support various facial related problems, i. e. unconstrained face recognition, facial periocular recognition, facial landmarking and pose estimation, facial expression recognition, 3D facial model construction, etc.

Face Detection Face Recognition +6

Unitary-Group Invariant Kernels and Features from Transformed Unlabeled Data

no code implementations18 Nov 2015 Dipan K. Pal, Marios Savvides

The study of representations invariant to common transformations of the data is important to learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.