Search Results for author:
Found 18 papers, 8 papers with code
Reducing Label Dependency for Underwater Scene Understanding: A Survey of Datasets, Techniques and Applications
In recent years, some works have performed automated analysis of underwater imagery, and a smaller number of studies have focused on weakly supervised approaches which aim to reduce the expert-provided labelled data required.
Temporal Attention for Cross-View Sequential Image Localization
This paper introduces a novel approach to enhancing cross-view localization, focusing on the fine-grained, sequential localization of street-view images within a single known satellite image patch, a significant departure from traditional one-to-one image retrieval methods.
Human-in-the-Loop Segmentation of Multi-species Coral Imagery
On the semantic segmentation task, we outperform the prior state-of-the-art by 8. 8% for pixel accuracy and by 13. 5% for mIoU when only 5 point labels are used for point label propagation.
Image Labels Are All You Need for Coarse Seagrass Segmentation
Our method outperforms previous approaches that require patch-level labels on the multi-species 'DeepSeagrass' dataset by 6. 8% (absolute) for the class-weighted F1 score, and by 12. 1% (absolute) for the seagrass presence/absence F1 score on the 'Global Wetlands' dataset.
Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery
We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model.
Going Deeper into Semi-supervised Person Re-identification
To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled.
Learning and Executing Re-usable Behaviour Trees from Natural Language Instruction
In this paper we demonstrate how behaviour trees, a well established control architecture in the fields of gaming and robotics, can be used in conjunction with natural language instruction to provide a robust and modular control architecture for instructing autonomous agents to learn and perform novel complex tasks.
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.
Semi-supervised Keypoint Localization
Keypoint representations are learnt with a semantic keypoint consistency constraint that forces the keypoint detection network to learn similar features for the same keypoint across the dataset.
ECG-Based Driver Stress Levels Detection System Using Hyperparameter Optimization
Our approach is to propose a framework based on Particle Swarm Optimization algorithm (PSO) to select an optimal/near optimal windowing hyperparameters values.
Sparse Convolutions on Continuous Domains for Point Cloud and Event Stream Networks
Image convolutions have been a cornerstone of a great number of deep learning advances in computer vision.
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.
Keypoint-Aligned Embeddings for Image Retrieval and Re-identification
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification.
Learning landmark guided embeddings for animal re-identification
Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively.
Improved Reinforcement Learning with Curriculum
Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner.
Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings
We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes.
Towards the Targeted Environment-Specific Evolution of Robot Components
This research considers the task of evolving the physical structure of a robot to enhance its performance in various environments, which is a significant problem in the field of Evolutionary Robotics.
Learning Free-Form Deformations for 3D Object Reconstruction
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge.
