Related papers: Filtering Empty Camera Trap Images in Embedded Sys…

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…

Embedding of large but redundant data, such as images or text, in a hierarchy of lower-dimensional spaces is one of the key features of representation learning approaches, which nowadays provide state-of-the-art solutions to problems once…

This study evaluates the inference performance of various deep learning models under an embedded system environment. In previous works, Multiply-Accumulate operation is typically used to measure computational load of a deep model. According…

Deep neural networks are powerful tools to detect hidden patterns in data and leverage them to make predictions, but they are not designed to understand uncertainty and estimate reliable probabilities. In particular, they tend to be…

Existing methods for enhancing dark images captured in a very low-light environment assume that the intensity level of the optimal output image is known and already included in the training set. However, this assumption often does not hold,…

Data acquisition in animal ecology is rapidly accelerating due to inexpensive and accessible sensors such as smartphones, drones, satellites, audio recorders and bio-logging devices. These new technologies and the data they generate hold…

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training…

We explore the field of wildlife re-identification by implementing an MLP from scratch using NumPy, A DCNN using Keras, and a binary classifier with LightGBM for the purpose of learning for an assignment. Analyzing the performance of…

We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…

Continual learning approaches help deep neural network models adapt and learn incrementally by trying to solve catastrophic forgetting. However, whether these existing approaches, applied traditionally to image-based tasks, work with the…

When imaging through a semi-reflective medium such as glass, the reflection of another scene can often be found in the captured images. It degrades the quality of the images and affects their subsequent analyses. In this paper, a novel deep…

Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in…

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional…

Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…

Developing artificial intelligence (AI) and machine learning (ML) models for medical imaging typically involves extensive training and testing on large datasets, consuming significant computational time, energy, and resources. There is a…

The reliable measurement of confidence in classifiers' predictions is very important for many applications and is, therefore, an important part of classifier design. Yet, although deep learning has received tremendous attention in recent…

While capable of segregating visual data, humans take time to examine a single piece, let alone thousands or millions of samples. The deep learning models efficiently process sizeable information with the help of modern-day computing.…

Image registration plays an important role in comparing images. It is particularly important in analyzing medical images like CT, MRI, PET, etc. to quantify different biological samples, to monitor disease progression and to fuse different…