Search Results for author:
Found 42 papers, 21 papers with code
Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking
This is particularly critical for complex tasks like object tracking, and the scarcity of large datasets in the hyperspectral domain acts as a bottleneck in achieving the full potential of powerful transformer models.
Inductive Graph Few-shot Class Incremental Learning
Thus, we propose a novel method, called Topology-based class Augmentation and Prototype calibration (TAP).
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Spatioformer: A Geo-encoded Transformer for Large-Scale Plant Species Richness Prediction
The results demonstrate that geolocational information is advantageous in predicting species richness from satellite observations over large spatial scales.
Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking.
Ranked #1 on
Visual Place Recognition
on Pittsburgh-30k-test
M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning
Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps.
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings
We propose PseudoNeg-MAE, a novel self-supervised learning framework that enhances global feature representation of point cloud mask autoencoder by making them both discriminative and sensitive to transformations.
Learning Compact Channel Correlation Representation for LiDAR Place Recognition
This paper presents a novel approach to learn compact channel correlation representation for LiDAR place recognition, called C3R, aimed at reducing the computational burden and dimensionality associated with traditional covariance pooling methods for place recognition tasks.
SOLVR: Submap Oriented LiDAR-Visual Re-Localisation
This paper proposes SOLVR, a unified pipeline for learning based LiDAR-Visual re-localisation which performs place recognition and 6-DoF registration across sensor modalities.
Object Registration in Neural Fields
Neural fields provide a continuous scene representation of 3D geometry and appearance in a way which has great promise for robotics applications.
Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields
Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene.
WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments
Recent progress in semantic scene understanding has primarily been enabled by the availability of semantically annotated bi-modal (camera and LiDAR) datasets in urban environments.
TULIP: Transformer for Upsampling of LiDAR Point Clouds
In this paper, we propose TULIP, a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input.
Pre-training with Random Orthogonal Projection Image Modeling
In this paper, we propose an Image Modeling framework based on random orthogonal projection instead of binary masking as in MIM.
Multivariate Prototype Representation for Domain-Generalized Incremental Learning
Deep learning models suffer from catastrophic forgetting when being fine-tuned with samples of new classes.
FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining
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
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.
GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors
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
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.
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
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.
Exploiting Field Dependencies for Learning on Categorical Data
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
Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem often encountered by covariance matrix estimation in CNN.
Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization
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.
Uncertainty-Aware Lidar Place Recognition in Novel Environments
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
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.
Quantitative Assessment of DESIS Hyperspectral Data for Plant Biodiversity Estimation in Australia
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
Using this framework, we investigate why Faster R-CNN and RetinaNet fail to detect objects in benchmark vision datasets and robotics datasets.
InCloud: Incremental Learning for Point Cloud Place Recognition
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.
Point Cloud Segmentation Using Sparse Temporal Local Attention
Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment.
The CSIRO Crown-of-Thorn Starfish Detection Dataset
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.
Dense Uncertainty Estimation
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.
LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition
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.
DeepSeagrass Dataset
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
Underwater surveys conducted using divers or robots equipped with customized camera payloads can generate a large number of images.
Scalable learning for bridging the species gap in image-based plant phenotyping
This study is applicable to use of synthetic data for automating the measurement of phenotypic traits.
Temporally Coherent Embeddings for Self-Supervised Video Representation Learning
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.
Ranked #37 on
Self-Supervised Action Recognition
on UCF101
Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach
The demand for multimodal sensing systems for robotics is growing due to the increase in robustness, reliability and accuracy offered by these systems.
Synthetic Human Model Dataset for Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction
We introduce a synthetic dataset for evaluating non-rigid 3D human reconstruction based on conventional RGB-D cameras.
Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction
We propose a puppet model-based tracking approach using skeleton prior, which provides a better initialization for tracking articulated movements.
Deep Leaf Segmentation Using Synthetic Data
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).
Non-rigid Reconstruction with a Single Moving RGB-D Camera
Our approach uses camera pose estimated from the rigid background for foreground tracking.
Elastic LiDAR Fusion: Dense Map-Centric Continuous-Time SLAM
The concept of continuous-time trajectory representation has brought increased accuracy and efficiency to multi-modal sensor fusion in modern SLAM.
Robotics
