Frederic Maire

Scarlett Raine, Ross Marchant, Brano Kusy et al.

Seagrass meadows serve as critical carbon sinks, but estimating the amount of carbon they store requires knowledge of the seagrass species present. Underwater and surface vehicles equipped with machine learning algorithms can help to accurately estimate the composition and extent of seagrass meadows at scale. However, previous approaches for seagrass detection and classification have required supervision from patch-level labels. In this paper, we reframe seagrass classification as a weakly supervised coarse segmentation problem where image-level labels are used during training (25 times fewer labels compared to patch-level labeling) and patch-level outputs are obtained at inference time. To this end, we introduce SeaFeats, an architecture that uses unsupervised contrastive pre-training and feature similarity, and SeaCLIP, a model that showcases the effectiveness of large language models as a supervisory signal in domain-specific applications. We demonstrate that an ensemble of SeaFeats and SeaCLIP leads to highly robust performance. 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 also present two case studies for real-world deployment: outlier detection on the Global Wetlands dataset, and application of our method on imagery collected by the FloatyBoat autonomous surface vehicle.

Dong Yuan, Frederic Maire, Feras Dayoub

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. By expanding to sequential image fine-grained localization, our model, equipped with a novel Temporal Attention Module (TAM), leverages contextual information to significantly improve sequential image localization accuracy. Our method shows substantial reductions in both mean and median localization errors on the Cross-View Image Sequence (CVIS) dataset, outperforming current state-of-the-art single-image localization techniques. Additionally, by adapting the KITTI-CVL dataset into sequential image sets, we not only offer a more realistic dataset for future research but also demonstrate our model's robust generalization capabilities across varying times and areas, evidenced by a 75.3% reduction in mean distance error in cross-view sequential image localization.

Scarlett Raine, Ross Marchant, Peyman Moghadam et al.

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. The images are labelled at the image-level by collecting images of the same morphotype in a folder hierarchy. We also release pre-trained models and training codes for detection and classification of seagrass species at the patch level at https://github.com/csiro-robotics/deepseagrass.

Scarlett Raine, Ross Marchant, Peyman Moghadam et al.

Underwater surveys conducted using divers or robots equipped with customized camera payloads can generate a large number of images. Manual review of these images to extract ecological data is prohibitive in terms of time and cost, thus providing strong incentive to automate this process using machine learning solutions. In this paper, we introduce a multi-species detector and classifier for seagrasses based on a deep convolutional neural network (achieved an overall accuracy of 92.4%). We also introduce a simple method to semi-automatically label image patches and therefore minimize manual labelling requirement. We describe and release publicly the dataset collected in this study as well as the code and pre-trained models to replicate our experiments at: https://github.com/csiro-robotics/deepseagrass

Scarlett Raine, Ross Marchant, Brano Kusy et al.

Marine surveys by robotic underwater and surface vehicles result in substantial quantities of coral reef imagery, however labeling these images is expensive and time-consuming for domain experts. Point label propagation is a technique that uses existing images labeled with sparse points to create augmented ground truth data, which can be used to train a semantic segmentation model. In this work, we show that recent advances in large foundation models facilitate the creation of augmented ground truth masks using only features extracted by the denoised version of the DINOv2 foundation model and K-Nearest Neighbors (KNN), without any pre-training. For images with extremely sparse labels, we present a labeling method based on human-in-the-loop principles, which greatly enhances annotation efficiency: in the case that there are 5 point labels per image, our human-in-the-loop method outperforms the prior state-of-the-art by 14.2% for pixel accuracy and 19.7% for mIoU; and by 8.9% and 18.3% if there are 10 point labels. When human-in-the-loop labeling is not available, using the denoised DINOv2 features with a KNN still improves on the prior state-of-the-art by 2.7% for pixel accuracy and 5.8% for mIoU (5 grid points). 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. Additionally, we perform a comprehensive study into the impacts of the point label placement style and the number of points on the point label propagation quality, and make several recommendations for improving the efficiency of labeling images with points.

Scarlett Raine, Frederic Maire, Niko Suenderhauf et al.

Underwater surveys provide long-term data for informing management strategies, monitoring coral reef health, and estimating blue carbon stocks. Advances in broad-scale survey methods, such as robotic underwater vehicles, have increased the range of marine surveys but generate large volumes of imagery requiring analysis. Computer vision methods such as semantic segmentation aid automated image analysis, but typically rely on fully supervised training with extensive labelled data. While ground truth label masks for tasks like street scene segmentation can be quickly and affordably generated by non-experts through crowdsourcing services like Amazon Mechanical Turk, ecology presents greater challenges. The complexity of underwater images, coupled with the specialist expertise needed to accurately identify species at the pixel level, makes this process costly, time-consuming, and heavily dependent on domain experts. 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. This survey focuses on approaches which reduce dependency on human expert input, while reviewing the prior and related approaches to position these works in the wider field of underwater perception. Further, we offer an overview of coastal ecosystems and the challenges of underwater imagery. We provide background on weakly and self-supervised deep learning and integrate these elements into a taxonomy that centres on the intersection of underwater monitoring, computer vision, and deep learning, while motivating approaches for weakly supervised deep learning with reduced dependency on domain expert data annotations. Lastly, the survey examines available datasets and platforms, and identifies gaps, barriers, and opportunities for automating underwater surveys.

Scarlett Raine, Ross Marchant, Brano Kusy et al.

Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images. Analysis of this imagery can be automated using a model trained to perform semantic segmentation, however it is too costly and time-consuming to densely label images for training supervised models. In this letter, we leverage photo-quadrat imagery labeled by ecologists with sparse point labels. We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth for training a semantic segmentation model. Our point label aware superpixel method utilizes the sparse point labels, and clusters pixels using learned features to accurately generate single-species segments in cluttered, complex coral images. Our method outperforms prior methods on the UCSD Mosaics dataset by 3.62% for pixel accuracy and 8.35% for mean IoU for the label propagation task, while reducing computation time reported by previous approaches by 76%. We train a DeepLabv3+ architecture and outperform state-of-the-art for semantic segmentation by 2.91% for pixel accuracy and 9.65% for mean IoU on the UCSD Mosaics dataset and by 4.19% for pixel accuracy and 14.32% mean IoU for the Eilat dataset.

Shahnewaz Ali, Ross Crawford, Frederic Maire et al.

Tissue awareness has a great demand to improve surgical accuracy in minimally invasive procedures. In arthroscopy, it is one of the challenging tasks due to surgical sites exhibit limited features and textures. Moreover, arthroscopic surgical video shows high intra-class variations. Arthroscopic videos are recorded with endoscope known as arthroscope which records tissue structures at proximity, therefore, frames contain minimal joint structure. As consequences, fully conventional network-based segmentation model suffers from long- and short- term dependency problems. In this study, we present a densely connected shape aware multi-scale segmentation model which captures multi-scale features and integrates shape features to achieve tissue-tool segmentations. The model has been evaluated with three distinct datasets. Moreover, with the publicly available polyp dataset our proposed model achieved 5.09 % accuracy improvement.

Olga Moskvyak, Frederic Maire, Feras Dayoub et al.

Person re-identification is the challenging task of identifying a person across different camera views. Training a convolutional neural network (CNN) for this task requires annotating a large dataset, and hence, it involves the time-consuming manual matching of people across cameras. 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. We conduct a comprehensive survey in the area of person re-identification with limited labels. Existing works in this realm are limited in the sense that they utilize features from multiple CNNs and require the number of identities in the unlabeled data to be known. To overcome these limitations, we propose to employ part-based features from a single CNN without requiring the knowledge of the label space (i.e., the number of identities). This makes our approach more suitable for practical scenarios, and it significantly reduces the need for computational resources. We also propose a PartMixUp loss that improves the discriminative ability of learned part-based features for pseudo-labeling in semi-supervised settings. Our method outperforms the state-of-the-art results on three large-scale person re-id datasets and achieves the same level of performance as fully supervised methods with only one-third of labeled identities.

Gavin Suddrey, Ben Talbot, Frederic Maire

Domestic and service robots have the potential to transform industries such as health care and small-scale manufacturing, as well as the homes in which we live. However, due to the overwhelming variety of tasks these robots will be expected to complete, providing generic out-of-the-box solutions that meet the needs of every possible user is clearly intractable. To address this problem, robots must therefore not only be capable of learning how to complete novel tasks at run-time, but the solutions to these tasks must also be informed by the needs of the user. 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 also show how behaviour trees generated using our approach can be generalised to novel scenarios, and can be re-used in future learning episodes to create increasingly complex behaviours. We validate this work against an existing corpus of natural language instructions, demonstrate the application of our approach on both a simulated robot solving a toy problem, as well as two distinct real-world robot platforms which, respectively, complete a block sorting scenario, and a patrol scenario.

Olga Moskvyak, Frederic Maire, Feras Dayoub et al.

Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that exhibit large variations in poses that greatly influence their visual appearance, such as wild animals. However, supervised training of a keypoint detection network requires annotating a large image dataset for each animal species, which is a labor-intensive task. To reduce the need for labeled data, we propose to learn simultaneously keypoint heatmaps and pose invariant keypoint representations in a semi-supervised manner using a small set of labeled images along with a larger set of unlabeled images. 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. Pose invariance is achieved by making keypoint representations for the image and its augmented copies closer together in feature space. Our semi-supervised approach significantly outperforms previous methods on several benchmarks for human and animal body landmark localization.

Mohammad Naim Rastgoo, Bahareh Nakisa, Andry Rakotonirainy et al.

Stress and driving are a dangerous combination which can lead to crashes, as evidenced by the large number of road traffic crashes that involve stress. Motivated by the need to address the significant costs of driver stress, it is essential to build a practical system that can classify driver stress level with high accuracy. However, the performance of an accurate driving stress levels classification system depends on hyperparameter optimization choices such as data segmentation (windowing hyperparameters). The configuration setting of hyperparameters, which has an enormous impact on the system performance, are typically hand-tuned while evaluating the algorithm. This tuning process is time consuming and often depends on personal experience. There are also no generic optimal values for hyperparameters values. In this work, we propose a meta-heuristic approach to support automated hyperparameter optimization and provide a real-time driver stress detection system. This is the first systematic study of optimizing windowing hyperparameters based on Electrocardiogram (ECG) signal in the domain of driving safety. Our approach is to propose a framework based on Particle Swarm Optimization algorithm (PSO) to select an optimal/near optimal windowing hyperparameters values. The performance of the proposed framework is evaluated on two datasets: a public dataset (DRIVEDB dataset) and our collected dataset using an advanced simulator. DRIVEDB dataset was collected in a real time driving scenario, and our dataset was collected using an advanced driving simulator in the control environment. We demonstrate that optimising the windowing hyperparameters yields significant improvement in terms of accuracy. The most accurate built model applied to the public dataset and our dataset, based on the selected windowing hyperparameters, achieved 92.12% and 77.78% accuracy, respectively.

Dominic Jack, Frederic Maire, Simon Denman et al.

Image convolutions have been a cornerstone of a great number of deep learning advances in computer vision. The research community is yet to settle on an equivalent operator for sparse, unstructured continuous data like point clouds and event streams however. We present an elegant sparse matrix-based interpretation of the convolution operator for these cases, which is consistent with the mathematical definition of convolution and efficient during training. On benchmark point cloud classification problems we demonstrate networks built with these operations can train an order of magnitude or more faster than top existing methods, whilst maintaining comparable accuracy and requiring a tiny fraction of the memory. We also apply our operator to event stream processing, achieving state-of-the-art results on multiple tasks with streams of hundreds of thousands of events.

Olga Moskvyak, Frederic Maire, Feras Dayoub et al.

Learning embeddings that are invariant to the pose of the object is crucial in visual image retrieval and re-identification. The existing approaches for person, vehicle, or animal re-identification tasks suffer from high intra-class variance due to deformable shapes and different camera viewpoints. To overcome this limitation, we propose to align the image embedding with a predefined order of the keypoints. The proposed keypoint aligned embeddings model (KAE-Net) learns part-level features via multi-task learning which is guided by keypoint locations. More specifically, KAE-Net extracts channels from a feature map activated by a specific keypoint through learning the auxiliary task of heatmap reconstruction for this keypoint. The KAE-Net is compact, generic and conceptually simple. It achieves state of the art performance on the benchmark datasets of CUB-200-2011, Cars196 and VeRi-776 for retrieval and re-identification tasks.

Olga Moskvyak, Frederic Maire, Feras Dayoub et al.

Re-identification of individual animals in images can be ambiguous due to subtle variations in body markings between different individuals and no constraints on the poses of animals in the wild. Person re-identification is a similar task and it has been approached with a deep convolutional neural network (CNN) that learns discriminative embeddings for images of people. However, learning discriminative features for an individual animal is more challenging than for a person's appearance due to the relatively small size of ecological datasets compared to labelled datasets of person's identities. We propose to improve embedding learning by exploiting body landmarks information explicitly. Body landmarks are provided to the input of a CNN as confidence heatmaps that can be obtained from a separate body landmark predictor. The model is encouraged to use heatmaps by learning an auxiliary task of reconstructing input heatmaps. Body landmarks guide a feature extraction network to learn the representation of a distinctive pattern and its position on the body. We evaluate the proposed method on a large synthetic dataset and a small real dataset. Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively. The method is robust to noise in input coordinates and can tolerate an error in coordinates up to 10% of the image size.

Joseph West, Frederic Maire, Cameron Browne et al.

Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions that lead to a terminal state (win, lose or draw). The advantage of learning end-games first is that once the actions which lead to a terminal state are understood, it becomes possible to incrementally learn the consequences of actions that are further away from a terminal state - we call this an end-game-first curriculum. Currently the state-of-the-art machine learning player for general board games, AlphaZero by Google DeepMind, does not employ a structured training curriculum; instead learning from the entire game at all times. By employing an end-game-first training curriculum to train an AlphaZero inspired player, we empirically show that the rate of learning of an artificial player can be improved during the early stages of training when compared to a player not using a training curriculum.

Olga Moskvyak, Frederic Maire, Asia O. Armstrong et al.

Visual identification of individual animals that bear unique natural body markings is an important task in wildlife conservation. The photo databases of animal markings grow larger and each new observation has to be matched against thousands of images. Existing photo-identification solutions have constraints on image quality and appearance of the pattern of interest in the image. These constraints limit the use of photos from citizen scientists. We present a novel system for visual re-identification based on unique natural markings that is robust to occlusions, viewpoint and illumination changes. We adapt methods developed for face re-identification and implement a deep convolutional neural network (CNN) to learn embeddings for images of natural markings. The distance between the learned embedding points provides a dissimilarity measure between the corresponding input images. The network is optimized using the triplet loss function and the online semi-hard triplet mining strategy. The proposed re-identification method is generic and not species specific. We evaluate the proposed system on image databases of manta ray belly patterns and humpback whale flukes. To be of practical value and adopted by marine biologists, a re-identification system needs to have a top-10 accuracy of at least 95%. The proposed system achieves this performance standard.

Jack Collins, Wade Geles, David Howard et al.

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. Inspired by the fields of evolutionary art and sculpture, we evolve only targeted parts of a robot, which simplifies the optimisation problem compared to traditional approaches that must simultaneously evolve both (actuated) body and brain. Exploration fidelity is emphasised in areas of the robot most likely to benefit from shape optimisation, whilst exploiting existing robot structure and control. Our approach uses a Genetic Algorithm to optimise collections of Bezier splines that together define the shape of a legged robot's tibia, and leg performance is evaluated in parallel in a high-fidelity simulator. The leg is represented in the simulator as 3D-printable file, and as such can be readily instantiated in reality. Provisional experiments in three distinct environments show the evolution of environment-specific leg structures that are both high-performing and notably different to those evolved in the other environments. This proof-of-concept represents an important step towards the environment-dependent optimisation of performance-critical components for a range of ubiquitous, standard, and already-capable robots that can carry out a wide variety of tasks.

Dominic Jack, Jhony K. Pontes, Sridha Sridharan et al.

Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly from advances in computer vision by generalizing 2D convolutions to the 3D setting, they also have several considerable drawbacks. The computational complexity of voxel-encodings grows cubically with the resolution thus limiting such representations to low-resolution 3D reconstruction. In an attempt to solve this problem, point cloud representations have been proposed. Although point clouds are more efficient than voxel representations as they only cover surfaces rather than volumes, they do not encode detailed geometric information about relationships between points. In this paper we propose a method to learn free-form deformations (FFD) for the task of 3D reconstruction from a single image. By learning to deform points sampled from a high-quality mesh, our trained model can be used to produce arbitrarily dense point clouds or meshes with fine-grained geometry. We evaluate our proposed framework on both synthetic and real-world data and achieve state-of-the-art results on point-cloud and volumetric metrics. Additionally, we qualitatively demonstrate its applicability to label transferring for 3D semantic segmentation.