Related papers: PhiNet v2: A Mask-Free Brain-Inspired Vision Found…

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous…

Deep hamming hashing has gained growing popularity in approximate nearest neighbour search for large-scale image retrieval. Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network…

Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key challenge in mirroring human cognition. To address this, we…

Self-supervised learning (SSL) methods aim to exploit the abundance of unlabelled data for machine learning (ML), however the underlying principles are often method-specific. An SSL framework derived from biological first principles of…

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems…

Reconstructing images seen by people from their fMRI brain recordings provides a non-invasive window into the human brain. Despite recent progress enabled by diffusion models, current methods often lack faithfulness to the actual seen…

General-purpose pre-trained models ("foundation models") have enabled practitioners to produce generalizable solutions for individual machine learning problems with datasets that are significantly smaller than those required for learning…

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic…

Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…

We propose V2CNet, a new deep learning framework to automatically translate the demonstration videos to commands that can be directly used in robotic applications. Our V2CNet has two branches and aims at understanding the demonstration…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

In this work we investigate the viability of foundational AI/ML models for Synthetic Aperture Radar (SAR) object recognition tasks. We are inspired by the tremendous progress being made in the wider community, particularly in the natural…

We develop a model for representing visual texture in a low-dimensional feature space, along with a novel self-supervised learning objective that is used to train it on an unlabeled database of texture images. Inspired by the architecture…

Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features…

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended…

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated…

Deep convolutional neural networks (DCNNs) have demonstrated excellent performance in object recognition and have been found to share some similarities with brain visual processing. However, the substantial gap between DCNNs and human…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…