Related papers: Fast Fishing: Approximating BAIT for Efficient and…

Branching Time Active Inference (Champion et al., 2021b,a) is a framework proposing to look at planning as a form of Bayesian model expansion. Its root can be found in Active Inference (Friston et al., 2016; Da Costa et al., 2020; Champion…

Active inference is a state-of-the-art framework for modelling the brain that explains a wide range of mechanisms such as habit formation, dopaminergic discharge and curiosity. However, recent implementations suffer from an exponential…

Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…

Active learning (AL) is an effective approach to select the most informative samples to label so as to reduce the annotation cost. Existing AL methods typically work under the closed-set assumption, i.e., all classes existing in the…

The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenges that exist at the algorithmic level. With growing interest…

Varying annotation costs among data points and budget constraints can hinder the adoption of active learning strategies in real-world applications. This work introduces two Bayesian active learning strategies for batch acquisition under…

Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework,…

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks…

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the…

Recent advancements in large-scale pretrained models have significantly improved performance across a variety of tasks in natural language processing and computer vision. However, the extensive number of parameters in these models…

Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these…

Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained…

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow…

Approximate Bayesian computation is an established and popular method for likelihood-free inference with applications in many disciplines. The effectiveness of the method depends critically on the availability of well performing summary…

As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. However, existing theoretical studies on AIL are primarily…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Automatic image-based severity estimation is an important task in computer-aided diagnosis. Severity estimation by deep learning requires a large amount of training data to achieve a high performance. In general, severity estimation uses…

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of such methods is limited…