Related papers: MENTOR: Human Perception-Guided Pretraining for In…
The human visual system is remarkably adept at adapting to changes in the input distribution; a capability modern convolutional neural networks (CNNs) still struggle to match. Drawing inspiration from the developmental trajectory of human…
Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…
How similar is the human mind to the sophisticated machine-learning systems that mirror its performance? Models of object categorization based on convolutional neural networks (CNNs) have achieved human-level benchmarks in assigning known…
We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…
Structural magnetic resonance imaging (MRI) studies have shown that Alzheimer's Disease (AD) induces both localised and widespread neural degenerative changes throughout the brain. However, the absence of segmentation that highlights brain…
Traditional self-supervised learning requires CNNs using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can…
Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmentation model is pretrained as a…
Multimodal emotion recognition study is hindered by the lack of labelled corpora in terms of scale and diversity, due to the high annotation cost and label ambiguity. In this paper, we propose a pre-training model \textbf{MEmoBERT} for…
This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting very general semantic concepts are available. We combine a…
Image memorability refers to the phenomenon where certain images are more likely to be remembered than others. It is a quantifiable and intrinsic image attribute, defined as the likelihood of an image being remembered upon a single…
Vision-language large models are moving toward the unification of visual understanding and visual generation tasks. However, whether generation can enhance understanding is still under-explored on large data scale. In this work, we analysis…
Transfer learning enables solving a specific task having limited data by using the pre-trained deep networks trained on large-scale datasets. Typically, while transferring the learned knowledge from source task to the target task, the last…
Scene understanding and object recognition is a difficult to achieve yet crucial skill for robots. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between their performance on…
Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…
A Convolutional Neural Network (CNN) is sometimes confronted with objects of changing appearance ( new instances) that exceed its generalization capability. This requires the CNN to incorporate new knowledge, i.e., to learn incrementally.…
The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human…
We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task…
The brain can only be fully understood through the lens of the behavior it generates -- a guiding principle in modern neuroscience research that nevertheless presents significant technical challenges. Many studies capture behavior with…
Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. These models achieve the current state of the art, but they have difficulties generalizing when applied to data that deviate from the…
Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…