Search Results for author: Mehrtash Harandi

Found 74 papers, 11 papers with code

On Modulating the Gradient for Meta-Learning

1 code implementation ECCV 2020 Christian Simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi

Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data.

Meta-Learning

On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation

no code implementations15 Jun 2022 Markus Hiller, Mehrtash Harandi, Tom Drummond

Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters.

Meta-Learning

Rethinking Generalization in Few-Shot Classification

1 code implementation15 Jun 2022 Markus Hiller, Rongkai Ma, Mehrtash Harandi, Tom Drummond

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted.

Classification Few-Shot Learning

GOSS: Towards Generalized Open-set Semantic Segmentation

no code implementations23 Mar 2022 Jie Hong, Weihao Li, Junlin Han, Jiyang Zheng, Pengfei Fang, Mehrtash Harandi, Lars Petersson

In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS).

Semantic Segmentation

Implicit Motion Handling for Video Camouflaged Object Detection

no code implementations CVPR 2022 Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, ZongYuan Ge

We propose a new video camouflaged object detection (VCOD) framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames.

Motion Estimation object-detection +2

On Generalizing Beyond Domains in Cross-Domain Continual Learning

no code implementations CVPR 2022 Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.

Continual Learning Knowledge Distillation

Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning

no code implementations7 Dec 2021 Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tom Drummond, Mehrtash Harandi

A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task.

Few-Shot Learning

Adaptive Poincaré Point to Set Distance for Few-Shot Classification

no code implementations3 Dec 2021 Rongkai Ma, Pengfei Fang, Tom Drummond, Mehrtash Harandi

To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively and based on the constellation of the points.

Few-Shot Learning

Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model

no code implementations22 Nov 2021 Jing Zhang, Yuchao Dai, Mehrtash Harandi, Yiran Zhong, Nick Barnes, Richard Hartley

Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty.

object-detection Object Detection

Learning Online for Unified Segmentation and Tracking Models

no code implementations12 Nov 2021 Tianyu Zhu, Rongkai Ma, Mehrtash Harandi, Tom Drummond

A segmentation model cannot easily learn from prior information given in the visual tracking scenario.

Meta-Learning online learning +1

Meta-Learning for Multi-Label Few-Shot Classification

no code implementations26 Oct 2021 Christian Simon, Piotr Koniusz, Mehrtash Harandi

Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address.

Classification Few-Shot Learning +1

Towards a Robust Differentiable Architecture Search under Label Noise

no code implementations23 Oct 2021 Christian Simon, Piotr Koniusz, Lars Petersson, Yan Han, Mehrtash Harandi

Our empirical evaluations show that the noise injecting operation does not degrade the performance of the NAS algorithm if the data is indeed clean.

Neural Architecture Search

Dense Uncertainty Estimation

1 code implementation13 Oct 2021 Jing Zhang, Yuchao Dai, Mochu Xiang, Deng-Ping Fan, Peyman Moghadam, Mingyi He, Christian Walder, Kaihao Zhang, Mehrtash Harandi, Nick Barnes

Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.

Decision Making

IDENTIFYING CONCEALED OBJECTS FROM VIDEOS

no code implementations29 Sep 2021 Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, ZongYuan Ge

The proposed SLT-Net leverages on both short-term dynamics and long-term temporal consistency to detect concealed objects in continuous video frames.

object-detection Object Detection

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

no code implementations20 Sep 2021 Jieming Zhou, Tong Zhang, Pengfei Fang, Lars Petersson, Mehrtash Harandi

The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors.

Semi-Supervised Metric Learning: A Deep Resurrection

no code implementations10 May 2021 Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar

In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples.

Metric Learning

Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions

no code implementations22 Apr 2021 Jing Wu, Mingyi Zhou, Ce Zhu, Yipeng Liu, Mehrtash Harandi, Li Li

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.

Adversarial Attack

On Learning the Geodesic Path for Incremental Learning

1 code implementation CVPR 2021 Christian Simon, Piotr Koniusz, Mehrtash Harandi

This in practice is done by minimizing the dissimilarity between current and previous responses of the network one way or another.

Incremental Learning Knowledge Distillation

Reinforced Attention for Few-Shot Learning and Beyond

no code implementations CVPR 2021 Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.

Few-Shot Learning Image Classification +1

Learning to Continually Learn Rapidly from Few and Noisy Data

1 code implementation6 Mar 2021 Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution.

Continual Learning Meta-Learning

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning

no code implementations CVPR 2021 Ali Cheraghian, Shafin Rahman, Pengfei Fang, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.

class-incremental learning Incremental Learning +2

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

no code implementations28 Feb 2021 Lie Ju, Xin Wang, Lin Wang, Dwarikanath Mahapatra, Xin Zhao, Mehrtash Harandi, Tom Drummond, Tongliang Liu, ZongYuan Ge

In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.

General Classification Image Classification +2

Highway-Connection Classifier Networks for Plastic yet Stable Continual Learning

no code implementations1 Jan 2021 Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

Catastrophic forgetting occurs when a neural network is trained sequentially on multiple tasks – its weights will be continuously modified and as a result, the network will lose its ability in solving a previous task.

Continual Learning

Kernel Methods in Hyperbolic Spaces

no code implementations ICCV 2021 Pengfei Fang, Mehrtash Harandi, Lars Petersson

However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e. g., computing the Frechet mean of a set of points requires an iterative algorithm).

Few-Shot Learning Knowledge Distillation +3

Curvature Generation in Curved Spaces for Few-Shot Learning

no code implementations ICCV 2021 Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi

Few-shot learning describes the challenging problem of recognizing samples from unseen classes given very few labeled examples.

Few-Shot Learning

Uncertainty-Aware Deep Calibrated Salient Object Detection

no code implementations10 Dec 2020 Jing Zhang, Yuchao Dai, Xin Yu, Mehrtash Harandi, Nick Barnes, Richard Hartley

Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy.

object-detection Object Detection +1

Set Augmented Triplet Loss for Video Person Re-Identification

no code implementations2 Nov 2020 Pengfei Fang, Pan Ji, Lars Petersson, Mehrtash Harandi

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss.

Metric Learning Video-Based Person Re-Identification

Hierarchical Neural Architecture Search for Deep Stereo Matching

1 code implementation NeurIPS 2020 Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, ZongYuan Ge

To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.

Neural Architecture Search Semantic Segmentation +2

Channel Recurrent Attention Networks for Video Pedestrian Retrieval

no code implementations7 Oct 2020 Pengfei Fang, Pan Ji, Jieming Zhou, Lars Petersson, Mehrtash Harandi

Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks.

Person Retrieval

Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss

no code implementations22 Aug 2020 Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar

As obtaining class labels in all applications is not feasible, we propose an unsupervised approach that learns a metric without making use of class labels.

Metric Learning

MTL2L: A Context Aware Neural Optimiser

1 code implementation18 Jul 2020 Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder, Gabriela Ferraro, Hanna Suominen

Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner.

Multi-Task Learning

Cross-Correlated Attention Networks for Person Re-Identification

no code implementations17 Jun 2020 Jieming Zhou, Soumava Kumar Roy, Pengfei Fang, Mehrtash Harandi, Lars Petersson

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered.

Person Re-Identification

Affinity guided Geometric Semi-Supervised Metric Learning

no code implementations27 Feb 2020 Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar

In this paper, we revamp the forgotten classical Semi-Supervised Distance Metric Learning (SSDML) problem from a Riemannian geometric lens, to leverage stochastic optimization within a end-to-end deep framework.

Metric Learning Riemannian optimization +1

A Probabilistic approach for Learning Embeddings without Supervision

no code implementations17 Dec 2019 Ujjal Kr Dutta, Mehrtash Harandi, Chandra Sekhar Chellu

This restricts their applicability for large datasets in new applications where obtaining labels require extensive manual efforts and domain knowledge.

Metric Learning Zero-Shot Learning

Projective Subspace Networks For Few-Shot Learning

no code implementations ICLR 2019 Christian Simon, Piotr Koniusz, Mehrtash Harandi

Generalization from limited examples, usually studied under the umbrella of meta-learning, equips learning techniques with the ability to adapt quickly in dynamical environments and proves to be an essential aspect of lifelong learning.

Few-Shot Learning General Classification

Neural Collaborative Subspace Clustering

no code implementations24 Apr 2019 Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li

We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces.

Scalable Deep $k$-Subspace Clustering

no code implementations2 Nov 2018 Tong Zhang, Pan Ji, Mehrtash Harandi, Richard Hartley, Ian Reid

In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm.

Block Mean Approximation for Efficient Second Order Optimization

no code implementations16 Apr 2018 Yao Lu, Mehrtash Harandi, Richard Hartley, Razvan Pascanu

Advanced optimization algorithms such as Newton method and AdaGrad benefit from second order derivative or second order statistics to achieve better descent directions and faster convergence rates.

Devon: Deformable Volume Network for Learning Optical Flow

no code implementations20 Feb 2018 Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions.

Optical Flow Estimation

Museum Exhibit Identification Challenge for Domain Adaptation and Beyond

no code implementations4 Feb 2018 Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang

To achieve robust baselines, we build on a recent approach that aligns per-class scatter matrices of the source and target CNN streams [15].

Domain Adaptation Few-Shot Learning

Generalized Rank Pooling for Activity Recognition

no code implementations CVPR 2017 Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen Gould

Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity.

Action Recognition Riemannian optimization

Learning an Invariant Hilbert Space for Domain Adaptation

no code implementations CVPR 2017 Samitha Herath, Mehrtash Harandi, Fatih Porikli

This paper introduces a learning scheme to construct a Hilbert space (i. e., a vector space along its inner product) to address both unsupervised and semi-supervised domain adaptation problems.

Domain Adaptation Riemannian optimization

Generalized BackPropagation, Étude De Cas: Orthogonality

no code implementations17 Nov 2016 Mehrtash Harandi, Basura Fernando

This paper introduces an extension of the backpropagation algorithm that enables us to have layers with constrained weights in a deep network.

Dimensionality Reduction Fine-Grained Image Classification +1

Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

1 code implementation3 Aug 2016 Wenbing Huang, Fuchun Sun, Lele Cao, Mehrtash Harandi

We then devise efficient algorithms to perform sparse coding and dictionary learning on the space of infinite-dimensional subspaces.

Dictionary Learning General Classification +4

Sparse Coding and Dictionary Learning With Linear Dynamical Systems

no code implementations CVPR 2016 Wenbing Huang, Fuchun Sun, Lele Cao, Deli Zhao, Huaping Liu, Mehrtash Harandi

To enhance the performance of LDSs, in this paper, we address the challenging issue of performing sparse coding on the space of LDSs, where both data and dictionary atoms are LDSs.

Dictionary Learning Video Classification

Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods

no code implementations20 May 2016 Mehrtash Harandi, Mathieu Salzmann, Richard Hartley

This lets us formulate dimensionality reduction as the problem of finding a projection that yields a low-dimensional manifold either with maximum discriminative power in the supervised scenario, or with maximum variance of the data in the unsupervised one.

Dimensionality Reduction

Going Deeper into Action Recognition: A Survey

no code implementations16 May 2016 Samitha Herath, Mehrtash Harandi, Fatih Porikli

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation.

Action Analysis Action Recognition +4

When VLAD met Hilbert

no code implementations CVPR 2016 Mehrtash Harandi, Mathieu Salzmann, Fatih Porikli

Vectors of Locally Aggregated Descriptors (VLAD) have emerged as powerful image/video representations that compete with or even outperform state-of-the-art approaches on many challenging visual recognition tasks.

General Classification

Riemannian Coding and Dictionary Learning: Kernels to the Rescue

no code implementations CVPR 2015 Mehrtash Harandi, Mathieu Salzmann

While sparse coding on non-flat Riemannian manifolds has recently become increasingly popular, existing solutions either are dedicated to specific manifolds, or rely on optimization problems that are difficult to solve, especially when it comes to dictionary learning.

Dictionary Learning

Optimizing Over Radial Kernels on Compact Manifolds

no code implementations CVPR 2014 Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification.

Computer Vision General Classification

A Framework for Shape Analysis via Hilbert Space Embedding

no code implementations13 Dec 2014 Sadeep Jayasumana, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold.

General Classification

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices

no code implementations CVPR 2013 Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

To encode the geometry of the manifold in the mapping, we introduce a family of provably positive definite kernels on the Riemannian manifold of SPD matrices.

Motion Segmentation Pedestrian Detection +1

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels

no code implementations30 Nov 2014 Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

We then use the proposed framework to identify positive definite kernels on two specific manifolds commonly encountered in computer vision: the Riemannian manifold of symmetric positive definite matrices and the Grassmann manifold, i. e., the Riemannian manifold of linear subspaces of a Euclidean space.

Computer Vision

Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences

no code implementations30 Aug 2014 Mehrtash Harandi, Richard Hartley, Brian Lovell, Conrad Sanderson

This paper introduces sparse coding and dictionary learning for Symmetric Positive Definite (SPD) matrices, which are often used in machine learning, computer vision and related areas.

Action Recognition Computer Vision +4

Kernel Coding: General Formulation and Special Cases

no code implementations30 Aug 2014 Mehrtash Harandi, Mathieu Salzmann

In contrast, here, we study the problem of performing coding in a high-dimensional Hilbert space, where the classes are expected to be more easily separable.

Dictionary Learning

Multi-Shot Person Re-Identification via Relational Stein Divergence

no code implementations4 Mar 2014 Azadeh Alavi, Yan Yang, Mehrtash Harandi, Conrad Sanderson

The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately.

General Classification Person Re-Identification

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds

no code implementations31 Jan 2014 Mehrtash Harandi, Richard Hartley, Chunhua Shen, Brian Lovell, Conrad Sanderson

With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds.

Action Recognition Classification +5

Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution

no code implementations18 Oct 2013 Mehrtash Harandi, Conrad Sanderson, Chunhua Shen, Brian C. Lovell

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry.

Action Recognition Computer Vision +5

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