Related papers: Using Human Perception to Regularize Transfer Lear…

Perceptual metrics are traditionally used to evaluate the quality of natural signals, such as images and audio. They are designed to mimic the perceptual behaviour of human observers and usually reflect structures found in natural signals.…

Traditional surveillance systems rely on human attention, limiting their effectiveness. This study employs convolutional neural networks and transfer learning to develop a real-time computer vision system for automatic handgun detection.…

In this paper, we propose an approach for transferring the knowledge of a neural model for sequence labeling, learned from the source domain, to a new model trained on a target domain, where new label categories appear. Our transfer…

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Due to the complexity of modeling the elastic properties of materials, the use of machine learning algorithms is continuously increasing for tactile sensing applications. Recent advances in deep neural networks applied to computer vision…

In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. In this paper, we explore training algorithms that instead optimize reward functions that explicitly…

Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a…

Lack of sufficient labeled data often limits the applicability of advanced machine learning algorithms to real life problems. However efficient use of Transfer Learning (TL) has been shown to be very useful across domains. TL utilizes…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Tactile representation learning (TRL) equips robots with the ability to leverage touch information, boosting performance in tasks such as environment perception and object manipulation. However, the heterogeneity of tactile sensors results…

Transfer learning is a very important tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet,…

Parameter estimation for dynamical systems remains challenging due to non-convexity and sensitivity to initial parameter guesses. Recent deep learning approaches enable accurate and fast parameter estimation but do not exploit transferable…

Learning with label proportions (LLP), which is a learning task that only provides unlabeled data in bags and each bag's label proportion, has widespread successful applications in practice. However, most of the existing LLP methods don't…

We introduce a new measure to evaluate the transferability of representations learned by classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy to compute: when given a classifier trained on a source data…

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…

Regularization and transfer learning are two popular techniques to enhance generalization on unseen data, which is a fundamental problem of machine learning. Regularization techniques are versatile, as they are task- and…

In many business settings, task-specific labeled data are scarce or costly to obtain, limiting supervised learning on a target task. A classical response is transfer learning (TL). Many TL works study how to transfer information from…

Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of…

We present a perception in reflection paradigm designed to transcend the limitations of current large vision-language models (LVLMs), which are expected yet often fail to achieve perfect perception initially. Specifically, we propose…