Search Results for author: Efstratios Gavves

Found 80 papers, 36 papers with code

Low Bias Low Variance Gradient Estimates for Hierarchical Boolean Stochastic Networks

no code implementations ICML 2020 Adeel Pervez, Taco Cohen, Efstratios Gavves

Stochastic neural networks with discrete random variables are an important class of models for their expressiveness and interpretability.

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

1 code implementation22 Aug 2023 Mohammadreza Salehi, Efstratios Gavves, Cees G. M. Snoek, Yuki M. Asano

Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning.

Self-Supervised Learning Unsupervised Semantic Segmentation

Neural Modulation Fields for Conditional Cone Beam Neural Tomography

no code implementations17 Jul 2023 Samuele Papa, David M. Knigge, Riccardo Valperga, Nikita Moriakov, Miltos Kofinas, Jan-Jakob Sonke, Efstratios Gavves

Conventional Computed Tomography (CT) methods require large numbers of noise-free projections for accurate density reconstructions, limiting their applicability to the more complex class of Cone Beam Geometry CT (CBCT) reconstruction.

Computed Tomography (CT)

Learning Lie Group Symmetry Transformations with Neural Networks

1 code implementation4 Jul 2023 Alex Gabel, Victoria Klein, Riccardo Valperga, Jeroen S. W. Lamb, Kevin Webster, Rick Quax, Efstratios Gavves

The problem of detecting and quantifying the presence of symmetries in datasets is useful for model selection, generative modeling, and data analysis, amongst others.

Model Selection

BISCUIT: Causal Representation Learning from Binary Interactions

1 code implementation16 Jun 2023 Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI.

Causal Discovery Causal Identification +1

Graph Switching Dynamical Systems

1 code implementation1 Jun 2023 Yongtuo Liu, Sara Magliacane, Miltiadis Kofinas, Efstratios Gavves

Dynamical systems with complex behaviours, e. g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes, each with simpler dynamics, and then learning the switching behaviour from one mode to another.

Time Series

PiClick: Picking the desired mask in click-based interactive segmentation

1 code implementation23 Apr 2023 Cilin Yan, Haochen Wang, Jie Liu, XiaoLong Jiang, Yao Hu, Xu Tang, Guoliang Kang, Efstratios Gavves

Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing.

Interactive Segmentation

Towards Open-Vocabulary Video Instance Segmentation

1 code implementation4 Apr 2023 Haochen Wang, Cilin Yan, Shuai Wang, XiaoLong Jiang, Xu Tang, Yao Hu, Weidi Xie, Efstratios Gavves

Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos.

Instance Segmentation Semantic Segmentation +1

Modulated Neural ODEs

no code implementations26 Feb 2023 Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories.

Friction Representation Learning

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

1 code implementation25 Jan 2023 David M. Knigge, David W. Romero, Albert Gu, Efstratios Gavves, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn, Jan-Jakob Sonke

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data.

Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

no code implementations9 Jan 2023 Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, Jan-Jakob Sonke, Efstratios Gavves

However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction.

Few-Shot Semantic Segmentation

Differentiable Mathematical Programming for Object-Centric Representation Learning

no code implementations5 Oct 2022 Adeel Pervez, Phillip Lippe, Efstratios Gavves

To solve the graph cuts our solution relies on an efficient, scalable, and differentiable quadratic programming approximation.

Object Discovery Representation Learning

Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computing

1 code implementation27 Jun 2022 Leonard Bereska, Efstratios Gavves

Our results suggest that reservoir computing is a promising candidate framework for the continual learning of dynamical systems.

Continual Learning

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

1 code implementation13 Jun 2022 Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e. g., as actions of an agent.

Causal Discovery Representation Learning +1

Towards a General Purpose CNN for Long Range Dependencies in $N$D

1 code implementation7 Jun 2022 David W. Romero, David M. Knigge, Albert Gu, Erik J. Bekkers, Efstratios Gavves, Jakub M. Tomczak, Mark Hoogendoorn

The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework.

Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection

1 code implementation28 May 2022 Hossein Mirzaei, Mohammadreza Salehi, Sajjad Shahabi, Efstratios Gavves, Cees G. M. Snoek, Mohammad Sabokrou, Mohammad Hossein Rohban

Effectiveness of our method for both the near-distribution and standard novelty detection is assessed through extensive experiments on datasets in diverse applications such as medical images, object classification, and quality control.

Ranked #2 on Anomaly Detection on One-class CIFAR-10 (using extra training data)

Anomaly Detection

Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

no code implementations CVPR 2022 Jie Liu, Yanqi Bao, Guo-Sen Xie, Huan Xiong, Jan-Jakob Sonke, Efstratios Gavves

Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels.

Few-Shot Semantic Segmentation Semantic Segmentation

NFormer: Robust Person Re-identification with Neighbor Transformer

1 code implementation CVPR 2022 Haochen Wang, Jiayi Shen, Yongtuo Liu, Yan Gao, Efstratios Gavves

To tackle this issue, we propose a Neighbor Transformer Network, or NFormer, which explicitly models interactions across all input images, thus suppressing outlier features and leading to more robust representations overall.

Person Re-Identification Representation Learning

3D Equivariant Graph Implicit Functions

no code implementations31 Mar 2022 Yunlu Chen, Basura Fernando, Hakan Bilen, Matthias Nießner, Efstratios Gavves

In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations.

Delta Distillation for Efficient Video Processing

no code implementations17 Mar 2022 Amirhossein Habibian, Haitam Ben Yahia, Davide Abati, Efstratios Gavves, Fatih Porikli

By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency trade-off for semantic segmentation and object detection in videos.

Knowledge Distillation object-detection +4

CITRIS: Causal Identifiability from Temporal Intervened Sequences

1 code implementation7 Feb 2022 Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments.

Representation Learning Temporal Sequences

Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

1 code implementation NeurIPS 2021 Miltiadis Kofinas, Naveen Shankar Nagaraja, Efstratios Gavves

Modelling interactions is critical in learning complex dynamical systems, namely systems of interacting objects with highly non-linear and time-dependent behaviour.

Trajectory Forecasting

Stability Regularization for Discrete Representation Learning

no code implementations ICLR 2022 Adeel Pervez, Efstratios Gavves

Stability regularization is method to make the output of continuous functions of Gaussian random variables close to discrete, that is binary or categorical, without the need for significant manual tuning.

Representation Learning

WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need

no code implementations13 Sep 2021 Yoni Schirris, Mendel Engelaer, Andreas Panteli, Hugo Mark Horlings, Efstratios Gavves, Jonas Teuwen

We present WeakSTIL, an interpretable two-stage weak label deep learning pipeline for scoring the percentage of stromal tumor infiltrating lymphocytes (sTIL%) in H&E-stained whole-slide images (WSIs) of breast cancer tissue.

Decision Making Multiple Instance Learning +2

Efficient Neural Causal Discovery without Acyclicity Constraints

2 code implementations ICLR 2022 Phillip Lippe, Taco Cohen, Efstratios Gavves

Learning the structure of a causal graphical model using both observational and interventional data is a fundamental problem in many scientific fields.

Causal Discovery

DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer

1 code implementation20 Jul 2021 Yoni Schirris, Efstratios Gavves, Iris Nederlof, Hugo Mark Horlings, Jonas Teuwen

For MSI prediction in a tumor-annotated and color normalized subset of TCGA-CRC (n=360 patients), contrastive self-supervised learning improves the tile supervision baseline from 0. 77 to 0. 87 AUROC, on par with our proposed DeepSMILE method.

Classification Multiple Instance Learning +2

Federated Mixture of Experts

no code implementations14 Jul 2021 Matthias Reisser, Christos Louizos, Efstratios Gavves, Max Welling

Federated learning (FL) has emerged as the predominant approach for collaborative training of neural network models across multiple users, without the need to gather the data at a central location.

Federated Learning

Unsharp Mask Guided Filtering

1 code implementation2 Jun 2021 Zenglin Shi, Yunlu Chen, Efstratios Gavves, Pascal Mettes, Cees G. M. Snoek

The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter.


Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel

1 code implementation26 Feb 2021 Changyong Oh, Roberto Bondesan, Efstratios Gavves, Max Welling

In this work we propose a batch Bayesian optimization method for combinatorial problems on permutations, which is well suited for expensive-to-evaluate objectives.

Bayesian Optimization Point Processes +1

Mixed Variable Bayesian Optimization with Frequency Modulated Kernels

no code implementations25 Feb 2021 Changyong Oh, Efstratios Gavves, Max Welling

In experiments, we demonstrate the improved sample efficiency of GP BO using FM kernels (BO-FM). On synthetic problems and hyperparameter optimization problems, BO-FM outperforms competitors consistently.

Bayesian Optimization Hyperparameter Optimization

Variance Reduction in Hierarchical Variational Autoencoders

no code implementations1 Jan 2021 Adeel Pervez, Efstratios Gavves

Variational autoencoders with deep hierarchies of stochastic layers have been known to suffer from the problem of posterior collapse, where the top layers fall back to the prior and become independent of input.

Rotation Equivariant Siamese Networks for Tracking

2 code implementations CVPR 2021 Deepak K. Gupta, Devanshu Arya, Efstratios Gavves

We further show that this change in orientation can be used to impose an additional motion constraint in Siamese tracking through imposing restriction on the change in orientation between two consecutive frames.

2D Pose Estimation Benchmarking +2

Siamese Tracking with Lingual Object Constraints

1 code implementation23 Nov 2020 Maximilian Filtenborg, Efstratios Gavves, Deepak Gupta

Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object.

Question Answering Video Summarization +2

Self-Selective Context for Interaction Recognition

no code implementations17 Oct 2020 Mert Kilickaya, Noureldien Hussein, Efstratios Gavves, Arnold Smeulders

Our experiments show that SSC leads to an important increase in interaction recognition performance, while using much fewer parameters.

Human-Object Interaction Detection

Categorical Normalizing Flows via Continuous Transformations

1 code implementation ICLR 2021 Phillip Lippe, Efstratios Gavves

Based on Categorical Normalizing Flows, we propose GraphCNF a permutation-invariant generative model on graphs.

Inductive Bias Variational Inference

PIC: Permutation Invariant Convolution for Recognizing Long-range Activities

no code implementations18 Mar 2020 Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

We study the three properties of PIC and demonstrate its effectiveness in recognizing the long-range activities of Charades, Breakfast, and MultiThumos.

Siamese Tracking of Cell Behaviour Patterns

no code implementations MIDL 2019 Andreas Panteli, Deepak K. Gupta, Nathan de Bruin, Efstratios Gavves

Tracking and segmentation of biological cells in video sequences is a challenging problem, especially due to the similarity of the cells and high levels of inherent noise.

Tracking-Assisted Segmentation of Biological Cells

no code implementations19 Oct 2019 Deepak K. Gupta, Nathan de Bruijn, Andreas Panteli, Efstratios Gavves

U-Net and its variants have been demonstrated to work sufficiently well in biological cell tracking and segmentation.

SafeCritic: Collision-Aware Trajectory Prediction

no code implementations15 Oct 2019 Tessa van der Heiden, Naveen Shankar Nagaraja, Christian Weiss, Efstratios Gavves

The Critic network is environmentally aware to prune trajectories that are in collision or are in violation with the environment.

Trajectory Prediction

Increasing Expressivity of a Hyperspherical VAE

no code implementations7 Oct 2019 Tim R. Davidson, Jakub M. Tomczak, Efstratios Gavves

Learning suitable latent representations for observed, high-dimensional data is an important research topic underlying many recent advances in machine learning.

3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation

no code implementations3 Oct 2019 Yunlu Chen, Thomas Mensink, Efstratios Gavves

We propose to model the effective receptive field of 2D convolution based on the scale and locality from the 3D neighborhood.

Semantic Segmentation

Low Bias Gradient Estimates for Very Deep Boolean Stochastic Networks

no code implementations25 Sep 2019 Adeel Pervez, Taco Cohen, Efstratios Gavves

In this work we focus on stochastic networks with multiple layers of Boolean latent variables.

I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentation

no code implementations7 Aug 2019 Laurens Samson, Nanne van Noord, Olaf Booij, Michael Hofmann, Efstratios Gavves, Mohsen Ghafoorian

Adversarial training has been recently employed for realizing structured semantic segmentation, in which the aim is to preserve higher-level scene structural consistencies in dense predictions.

Semantic Segmentation

Model Decay in Long-Term Tracking

no code implementations5 Aug 2019 Efstratios Gavves, Ran Tao, Deepak K. Gupta, Arnold W. M. Smeulders

Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning.

VideoGraph: Recognizing Minutes-Long Human Activities in Videos

no code implementations13 May 2019 Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

To represent them, related works opt for statistical pooling, which neglects the temporal structure.

Initialized Equilibrium Propagation for Backprop-Free Training

no code implementations ICLR 2019 Peter O'Connor, Efstratios Gavves, Max Welling

In response to this, Scellier & Bengio (2017) proposed Equilibrium Propagation - a method for gradient-based train- ing of neural networks which uses only local learning rules and, crucially, does not rely on neurons having a mechanism for back-propagating an error gradient.

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

2 code implementations CVPR 2019 Shuai Liao, Efstratios Gavves, Cees G. M. Snoek

We observe many continuous output problems in computer vision are naturally contained in closed geometrical manifolds, like the Euler angles in viewpoint estimation or the normals in surface normal estimation.

3D Rotation Estimation regression +3

Combinatorial Bayesian Optimization using the Graph Cartesian Product

1 code implementation NeurIPS 2019 Changyong Oh, Jakub M. Tomczak, Efstratios Gavves, Max Welling

On this combinatorial graph, we propose an ARD diffusion kernel with which the GP is able to model high-order interactions between variables leading to better performance.

Bayesian Optimization Neural Architecture Search +1

Timeception for Complex Action Recognition

3 code implementations CVPR 2019 Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued.

Action Classification Action Recognition

Relaxed Quantization for Discretized Neural Networks

1 code implementation ICLR 2019 Christos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, Max Welling

Neural network quantization has become an important research area due to its great impact on deployment of large models on resource constrained devices.

General Classification Quantization

Dynamic Adaptation on Non-Stationary Visual Domains

no code implementations2 Aug 2018 Sindi Shkodrani, Michael Hofmann, Efstratios Gavves

To demonstrate the effectiveness of our proposed framework, we modify associative domain adaptation to work well on source and target data batches with unequal class distributions.

Domain Adaptation Semantic Segmentation

Video Time: Properties, Encoders and Evaluation

no code implementations18 Jul 2018 Amir Ghodrati, Efstratios Gavves, Cees G. M. Snoek

Time-aware encoding of frame sequences in a video is a fundamental problem in video understanding.

Video Understanding

BOCK : Bayesian Optimization with Cylindrical Kernels

1 code implementation ICML 2018 Changyong Oh, Efstratios Gavves, Max Welling

A major challenge in Bayesian Optimization is the boundary issue (Swersky, 2017) where an algorithm spends too many evaluations near the boundary of its search space.

Bayesian Optimization

Examining Cooperation in Visual Dialog Models

1 code implementation4 Dec 2017 Mircea Mironenco, Dana Kianfar, Ke Tran, Evangelos Kanoulas, Efstratios Gavves

In this work we propose a blackbox intervention method for visual dialog models, with the aim of assessing the contribution of individual linguistic or visual components.

Visual Dialog

Tracking for Half an Hour

1 code implementation28 Nov 2017 Ran Tao, Efstratios Gavves, Arnold W. M. Smeulders

Long-term tracking requires extreme stability to the multitude of model updates and robustness to the disappearance and loss of the target as such will inevitably happen.

Temporally Efficient Deep Learning with Spikes

1 code implementation ICLR 2018 Peter O'Connor, Efstratios Gavves, Max Welling

We present a variant on backpropagation for neural networks in which computation scales with the rate of change of the data - not the rate at which we process the data.

Action Recognition with Dynamic Image Networks

3 code implementations2 Dec 2016 Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi

This is a powerful idea because it allows to convert any video to an image so that existing CNN models pre-trained for the analysis of still images can be immediately extended to videos.

Action Recognition Optical Flow Estimation +1

Self-Supervised Video Representation Learning With Odd-One-Out Networks

no code implementations CVPR 2017 Basura Fernando, Hakan Bilen, Efstratios Gavves, Stephen Gould

On action classification, our method obtains 60. 3\% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current state-of-the-art self-supervised learning methods.

Action Classification General Classification +5

Dynamic Image Networks for Action Recognition

1 code implementation CVPR 2016 Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi, Stephen Gould

We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used.

Action Recognition Temporal Action Localization

Siamese Instance Search for Tracking

no code implementations CVPR 2016 Ran Tao, Efstratios Gavves, Arnold W. M. Smeulders

In this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated on the popular online tracking benchmark (OTB) and six very challenging YouTube videos.

Geometric Matching Instance Search

Online Action Detection

no code implementations21 Apr 2016 Roeland De Geest, Efstratios Gavves, Amir Ghodrati, Zhenyang Li, Cees Snoek, Tinne Tuytelaars

Third, the start of the action is unknown, so it is unclear over what time window the information should be integrated.

Online Action Detection

Rank Pooling for Action Recognition

1 code implementation6 Dec 2015 Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati, Tinne Tuytelaars

We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation.

Action Recognition Gesture Recognition +2

Learning to Rank Based on Subsequences

no code implementations ICCV 2015 Basura Fernando, Efstratios Gavves, Damien Muselet, Tinne Tuytelaars

We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences.


MidRank: Learning to rank based on subsequences

no code implementations29 Nov 2015 Basura Fernando, Efstratios Gavves, Damien Muselet, Tinne Tuytelaars

We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences.


Deep Reflectance Maps

no code implementations CVPR 2016 Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Efstratios Gavves, Tinne Tuytelaars

Undoing the image formation process and therefore decomposing appearance into its intrinsic properties is a challenging task due to the under-constraint nature of this inverse problem.

Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks

no code implementations ICCV 2015 Efstratios Gavves, Thomas Mensink, Tatiana Tommasi, Cees G. M. Snoek, Tinne Tuytelaars

How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data?

Active Learning General Classification +2

Modeling Video Evolution for Action Recognition

no code implementations CVPR 2015 Basura Fernando, Efstratios Gavves, Jose Oramas M., Amir Ghodrati, Tinne Tuytelaars

We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video.

Action Recognition Skeleton Based Action Recognition +1

COSTA: Co-Occurrence Statistics for Zero-Shot Classification

no code implementations CVPR 2014 Thomas Mensink, Efstratios Gavves, Cees G. M. Snoek

In this paper we aim for zero-shot classification, that is visual recognition of an unseen class by using knowledge transfer from known classes.

Classification Few-Shot Learning +3

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