Related papers: MENTOR: Human Perception-Guided Pretraining for In…

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…

We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network (CNN). To comprehend a CNN, the GAN is trained with information on how the CNN…

Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…

One of the largest problems in medical image processing is the lack of annotated data. Labeling medical images often requires highly trained experts and can be a time-consuming process. In this paper, we evaluate a method of reducing the…

Datasets are crucial when training a deep neural network. When datasets are unrepresentative, trained models are prone to bias because they are unable to generalise to real world settings. This is particularly problematic for models trained…

While convolutional neural networks (CNNs) have come to match and exceed human performance in many settings, the tasks these models optimize for are largely constrained to the level of individual objects, such as classification and…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very…

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Neural networks transform high-dimensional data into compact, structured representations, often modeled as elements of a lower dimensional latent space. In this paper, we present an alternative interpretation of neural models as dynamical…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…

Recently, foundation models have been introduced demonstrating various tasks in the field of computer vision. These models such as Segment Anything Model (SAM) are generalized models trained using huge datasets. Currently, ongoing research…

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Purpose: The aim of this work is to develop a neural network training framework for continual training of small amounts of medical imaging data and create heuristics to assess training in the absence of a hold-out validation or test set.…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typically provides only class-level labels, allowing models to achieve high accuracy through…

Convolutional neural networks demonstrated outstanding empirical results in computer vision and speech recognition tasks where labeled training data is abundant. In medical imaging, there is a huge variety of possible imaging modalities and…

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…