A collision avoidance system based on simple digital cameras would help enable the safe integration of small UAVs into crowded, low-altitude environments. In this work, we present an obstacle avoidance system for small UAVs that uses a monocular camera with a hybrid neural network and path planner controller. The system is comprised of a vision network for estimating depth from camera images, a high-level control network, a collision prediction network, and a contingency policy. This system is evaluated on a simulated UAV navigating an obstacle course in a constrained flight pattern. Results show the proposed system achieves low collision rates while maintaining operationally relevant flight speeds.

In this work we introduce attention as a state of the art mechanism for classification of radio galaxies using convolutional neural networks. We present an attention-based model that performs on par with previous classifiers while using more than 50\% fewer parameters than the next smallest classic CNN application in this field. We demonstrate quantitatively how the selection of normalisation and aggregation methods used in attention-gating can affect the output of individual models, and show that the resulting attention maps can be used to interpret the classification choices made by the model. We observe that the salient regions identified by the our model align well with the regions an expert human classifier would attend to make equivalent classifications. We show that while the selection of normalisation and aggregation may only minimally affect the performance of individual models, it can significantly affect the interpretability of the respective attention maps and by selecting a model which aligns well with how astronomers classify radio sources by eye, a user can employ the model in a more effective manner.

In this work, we analyze if it is possible to distinguish between different clones of the same bacteria species (Klebisiella pneumoniae) based only on microscopic images. It is a challenging task, previously considered impossible due to the high clones' similarity. For this purpose, we apply a multi-step algorithm with attention-based multiple instance learning. Except for obtaining accuracy at the level of 0.9, we introduce extensive interpretability based on CellProfiler and persistence homology, increasing the understandability and trust in the model.

During the training phase of machine learning (ML) models, it is usually necessary to configure several hyperparameters. This process is computationally intensive and requires an extensive search to infer the best hyperparameter set for the given problem. The challenge is exacerbated by the fact that most ML models are complex internally, and training involves trial-and-error processes that could remarkably affect the predictive result. Moreover, each hyperparameter of an ML algorithm is potentially intertwined with the others, and changing it might result in unforeseeable impacts on the remaining hyperparameters. Evolutionary optimization is a promising method to try and address those issues. According to this method, performant models are stored, while the remainder are improved through crossover and mutation processes inspired by genetic algorithms. We present VisEvol, a visual analytics tool that supports interactive exploration of hyperparameters and intervention in this evolutionary procedure. In summary, our proposed tool helps the user to generate new models through evolution and eventually explore powerful hyperparameter combinations in diverse regions of the extensive hyperparameter space. The outcome is a voting ensemble (with equal rights) that boosts the final predictive performance. The utility and applicability of VisEvol are demonstrated with two use cases and interviews with ML experts who evaluated the effectiveness of the tool.

The approach is based on learning a semantic similarity measure to find for a given test example the semantically closest example in the training set and then using a discriminator to classify whether the two examples show sufficient semantic dissimilarity such that the test example can be rejected as OOD. We are able to outperform previous approaches for anomaly, novelty, or out-of-distribution detection in the visual domain by a large margin. In particular we obtain AUROC values close to one for the challenging task of detecting examples from CIFAR-10 as out-of-distribution given CIFAR-100 as in-distribution, without making use of label information. Anomaly detection or novelty detection aims at identifying patterns in data that are significantly different to what is expected. This problem is inherently a binary classification problem that classifies examples either as in-distribution or out-of-distribution, given a sufficiently large sample from the in-distribution (training set). A natural approach to OOD detection is to learn a density model from the training data and compute the likelihood ratio of OOD examples to in-distribution examples.

This paper presents a novel alternative to Greedy Non-Maxima Suppression (NMS) in the task of bounding box selection and suppression in object detection. It proposes Confluence, an algorithm which does not rely solely on individual confidence scores to select optimal bounding boxes, nor does it rely on Intersection Over Union (IoU) to remove false positives. Using Manhattan Distance, it selects the bounding box which is closest to every other bounding box within the cluster and removes highly confluent neighboring boxes. Thus, Confluence represents a paradigm shift in bounding box selection and suppression as it is based on fundamentally different theoretical principles to Greedy NMS and its variants. Confluence is experimentally validated on RetinaNet, YOLOv3 and Mask-RCNN, using both the MS COCO and PASCAL VOC 2007 datasets. Confluence outperforms Greedy NMS in both mAP and recall on both datasets, using the challenging 0.50:0.95 mAP evaluation metric. On each detector and dataset, mAP was improved by 0.3-0.7% while recall was improved by 1.4-2.5%. A theoretical comparison of Greedy NMS and the Confluence Algorithm is provided, and quantitative results are supported by extensive qualitative results analysis. Furthermore, sensitivity analysis experiments across mAP thresholds support the conclusion that Confluence is more robust than NMS.

Beyond representing the external world, humans also represent their own cognitive processes. In the context of perception, this metacognition helps us identify unreliable percepts, such as when we recognize that we are seeing an illusion. Here we propose MetaGen, a model for the unsupervised learning of metacognition. In MetaGen, metacognition is expressed as a generative model of how a perceptual system produces noisy percepts. Using basic principles of how the world works (such as object permanence, part of infants' core knowledge), MetaGen jointly infers the objects in the world causing the percepts and a representation of its own perceptual system. MetaGen can then use this metacognition to infer which objects are actually present in the world. On simulated data, we find that MetaGen quickly learns a metacognition and improves overall accuracy, outperforming models that lack a metacognition.

Naturalistic driving data (NDD) is an important source of information to understand crash causation and human factors and to further develop crash avoidance countermeasures. Videos recorded while driving are often included in such datasets. While there is often a large amount of video data in NDD, only a small portion of them can be annotated by human coders and used for research, which underuses all video data. In this paper, we explored a computer vision method to automatically extract the information we need from videos. More specifically, we developed a 3D ConvNet algorithm to automatically extract cell-phone-related behaviors from videos. The experiments show that our method can extract chunks from videos, most of which (~79%) contain the automatically labeled cell phone behaviors. In conjunction with human review of the extracted chunks, this approach can find cell-phone-related driver behaviors much more efficiently than simply viewing video.

A statistical analysis of the observed perturbations in the density of stellar streams can in principle set stringent contraints on the mass function of dark matter subhaloes, which in turn can be used to constrain the mass of the dark matter particle. However, the likelihood of a stellar density with respect to the stream and subhaloes parameters involves solving an intractable inverse problem which rests on the integration of all possible forward realisations implicitly defined by the simulation model. In order to infer the subhalo abundance, previous analyses have relied on Approximate Bayesian Computation (ABC) together with domain-motivated but handcrafted summary statistics. Here, we introduce a likelihood-free Bayesian inference pipeline based on Amortised Approximate Likelihood Ratios (AALR), which automatically learns a mapping between the data and the simulator parameters and obviates the need to handcraft a possibly insufficient summary statistic. We apply the method to the simplified case where stellar streams are only perturbed by dark matter subhaloes, thus neglecting baryonic substructures, and describe several diagnostics that demonstrate the effectiveness of the new method and the statistical quality of the learned estimator.

This article is a follow up to my previous article about One Shot learning, Siamese networks and Triplet Loss with Keras. "One Shot Learning" and "Mining" are described there, so if you're not familiar with these concepts yet, I highly recommend you read that first. A friend of mine says that, to make significant progress in machine learning, one should read research papers on the field. While browsing research papers, I found this one "Beyond triplet loss: a deep quadruplet network for person re-identification" that seemed to be a source of improvement over my previous work and I decided to try to recreate what they have done but for my particular case. This article is about exploring the paper and implementing some of the concepts in the research paper with Keras.