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.
We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model.
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.
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.
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.
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.
Our approach is to propose a framework based on Particle Swarm Optimization algorithm (PSO) to select an optimal/near optimal windowing hyperparameters values.
Image convolutions have been a cornerstone of a great number of deep learning advances in computer vision.
Underwater surveys conducted using divers or robots equipped with customized camera payloads can generate a large number of images.
Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification.
Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively.
Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner.
We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes.
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.
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge.