Search Results for author: Peyman Moghadam

Found 30 papers, 17 papers with code

Pre-training with Random Orthogonal Projection Image Modeling

no code implementations28 Oct 2023 Maryam Haghighat, Peyman Moghadam, Shaheer Mohamed, Piotr Koniusz

In this paper, we propose an Image Modeling framework based on random orthogonal projection instead of binary masking as in MIM.

FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pre-Training

1 code implementation18 Sep 2023 Shaheer Mohamed, Maryam Haghighat, Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Peyman Moghadam

However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information.

Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition

no code implementations31 Aug 2023 Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam

This paper proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition methods.

Domain Adaptation Retrieval

GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors

1 code implementation9 Aug 2023 Joshua Knights, Stephen Hausler, Sridha Sridharan, Clinton Fookes, Peyman Moghadam

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak performance.


Subspace Distillation for Continual Learning

1 code implementation31 Jul 2023 Kaushik Roy, Christian Simon, Peyman Moghadam, Mehrtash Harandi

To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the account the manifold structure of the latent/output space of a neural network in learning novel tasks.

Continual Learning Knowledge Distillation +1

L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space

1 code implementation31 Jul 2023 Kaushik Roy, Peyman Moghadam, Mehrtash Harandi

To address the problem, we propose a distillation strategy named L3DMC that operates on mixed-curvature spaces to preserve the already-learned knowledge by modeling and maintaining complex geometrical structures.

Image Classification Medical Image Classification +1

Exploiting Field Dependencies for Learning on Categorical Data

1 code implementation18 Jul 2023 Zhibin Li, Piotr Koniusz, Lu Zhang, Daniel Edward Pagendam, Peyman Moghadam

Instead of modelling statistics of features globally (i. e., by the covariance matrix of features), we learn a global field dependency matrix that captures dependencies between fields and then we refine the global field dependency matrix at the instance-wise level with different weights (so-called local dependency modelling) w. r. t.


Learning Partial Correlation based Deep Visual Representation for Image Classification

1 code implementation CVPR 2023 Saimunur Rahman, Piotr Koniusz, Lei Wang, Luping Zhou, Peyman Moghadam, Changming Sun

Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem often encountered by covariance matrix estimation in CNN.

Fine-Grained Image Classification

Plant species richness prediction from DESIS hyperspectral data: A comparison study on feature extraction procedures and regression models

no code implementations5 Jan 2023 Yiqing Guo, Karel Mokany, Cindy Ong, Peyman Moghadam, Simon Ferrier, Shaun R. Levick

The advanced spectral and spatial specification of the recently launched DESIS (the DLR Earth Sensing Imaging Spectrometer) instrument provides a unique opportunity to test the potential for monitoring plant species diversity with spaceborne hyperspectral data.

GPR regression

Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization

1 code implementation10 Oct 2022 Kavisha Vidanapathirana, Peyman Moghadam, Sridha Sridharan, Clinton Fookes

We demonstrate how the optimal inter-cluster score of the correspondence compatibility graph of two point clouds represents a robust fitness score measuring their spatial consistency.

Point Cloud Registration Point Cloud Retrieval +3

Uncertainty-Aware Lidar Place Recognition in Novel Environments

1 code implementation4 Oct 2022 Keita Mason, Joshua Knights, Milad Ramezani, Peyman Moghadam, Dimity Miller

State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments.

A Real-time Edge-AI System for Reef Surveys

no code implementations1 Aug 2022 Yang Li, Jiajun Liu, Brano Kusy, Ross Marchant, Brendan Do, Torsten Merz, Joey Crosswell, Andy Steven, Lachlan Tychsen-Smith, David Ahmedt-Aristizabal, Jeremy Oorloff, Peyman Moghadam, Russ Babcock, Megha Malpani, Ard Oerlemans

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels.

object-detection Object Detection

Quantitative Assessment of DESIS Hyperspectral Data for Plant Biodiversity Estimation in Australia

no code implementations6 Jul 2022 Yiqing Guo, Karel Mokany, Cindy Ong, Peyman Moghadam, Simon Ferrier, Shaun R. Levick

Though remote sensing has been seen as a promising and cost-effective proxy for estimating plant diversity, there is a lack of quantitative studies on how confidently plant diversity can be inferred from spaceborne hyperspectral data.


What's in the Black Box? The False Negative Mechanisms Inside Object Detectors

1 code implementation15 Mar 2022 Dimity Miller, Peyman Moghadam, Mark Cox, Matt Wildie, Raja Jurdak

Using this framework, we investigate why Faster R-CNN and RetinaNet fail to detect objects in benchmark vision datasets and robotics datasets.

object-detection Object Detection +1

InCloud: Incremental Learning for Point Cloud Place Recognition

2 code implementations2 Mar 2022 Joshua Knights, Peyman Moghadam, Milad Ramezani, Sridha Sridharan, Clinton Fookes

In this paper we address the problem of incremental learning for point cloud place recognition and introduce InCloud, a structure-aware distillation-based approach which preserves the higher-order structure of the network's embedding space.

Incremental Learning

Point Cloud Segmentation Using Sparse Temporal Local Attention

no code implementations1 Dec 2021 Joshua Knights, Peyman Moghadam, Clinton Fookes, Sridha Sridharan

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment.

Autonomous Vehicles Point Cloud Segmentation

The CSIRO Crown-of-Thorn Starfish Detection Dataset

no code implementations29 Nov 2021 Jiajun Liu, Brano Kusy, Ross Marchant, Brendan Do, Torsten Merz, Joey Crosswell, Andy Steven, Nic Heaney, Karl Von Richter, Lachlan Tychsen-Smith, David Ahmedt-Aristizabal, Mohammad Ali Armin, Geoffrey Carlin, Russ Babcock, Peyman Moghadam, Daniel Smith, Tim Davis, Kemal El Moujahid, Martin Wicke, Megha Malpani

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are underway in an attempt to manage COTS populations to ecologically sustainable levels.

BIG-bench Machine Learning Management

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

LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition

1 code implementation17 Sep 2021 Kavisha Vidanapathirana, Milad Ramezani, Peyman Moghadam, Sridha Sridharan, Clinton Fookes

Experiments on two large-scale public benchmarks (KITTI and MulRan) show that our method achieves mean $F1_{max}$ scores of $0. 939$ and $0. 968$ on KITTI and MulRan respectively, achieving state-of-the-art performance while operating in near real-time.

3D Place Recognition Retrieval +1

DeepSeagrass Dataset

1 code implementation9 Mar 2021 Scarlett Raine, Ross Marchant, Peyman Moghadam, Frederic Maire, Brett Kettle, Brano Kusy

We introduce a dataset of seagrass images collected by a biologist snorkelling in Moreton Bay, Queensland, Australia, as described in our publication: arXiv:2009. 09924.

Multi-species Seagrass Detection and Classification from Underwater Images

1 code implementation18 Sep 2020 Scarlett Raine, Ross Marchant, Peyman Moghadam, Frederic Maire, Brett Kettle, Brano Kusy

Underwater surveys conducted using divers or robots equipped with customized camera payloads can generate a large number of images.

Classification General Classification

Temporally Coherent Embeddings for Self-Supervised Video Representation Learning

1 code implementation21 Mar 2020 Joshua Knights, Ben Harwood, Daniel Ward, Anthony Vanderkop, Olivia Mackenzie-Ross, Peyman Moghadam

The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding space, rather than indirectly learning it through ranking or predictive proxy tasks.

Metric Learning Representation Learning +3

Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach

no code implementations17 Jan 2020 Chanoh Park, Peyman Moghadam, Soohwan Kim, Sridha Sridharan, Clinton Fookes

The demand for multimodal sensing systems for robotics is growing due to the increase in robustness, reliability and accuracy offered by these systems.

Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction

no code implementations9 Oct 2018 Shafeeq Elanattil, Peyman Moghadam, Simon Denman, Sridha Sridharan, Clinton Fookes

We propose a puppet model-based tracking approach using skeleton prior, which provides a better initialization for tracking articulated movements.

3D Reconstruction

Deep Leaf Segmentation Using Synthetic Data

3 code implementations28 Jul 2018 Daniel Ward, Peyman Moghadam, Nicolas Hudson

Our proposed approach achieves 90% leaf segmentation score on the A1 test set outperforming the-state-of-the-art approaches for the CVPPP Leaf Segmentation Challenge (LSC).

Instance Segmentation Segmentation +2

Non-rigid Reconstruction with a Single Moving RGB-D Camera

no code implementations29 May 2018 Shafeeq Elanattil, Peyman Moghadam, Sridha Sridharan, Clinton Fookes, Mark Cox

Our approach uses camera pose estimated from the rigid background for foreground tracking.

Elastic LiDAR Fusion: Dense Map-Centric Continuous-Time SLAM

no code implementations6 Nov 2017 Chanoh Park, Peyman Moghadam, Soohwan Kim, Alberto Elfes, Clinton Fookes, Sridha Sridharan

The concept of continuous-time trajectory representation has brought increased accuracy and efficiency to multi-modal sensor fusion in modern SLAM.


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