Related papers: Local Learning on Transformers via Feature Reconst…

Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar…

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit…

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

We investigate the problem of representing an entire video using CNN features for human action recognition. Currently, limited by GPU memory, we have not been able to feed a whole video into CNN/RNNs for end-to-end learning. A common…

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Magnetic Resonance Imaging (MRI) is an important medical imaging modality, while it requires a long acquisition time. To reduce the acquisition time, various methods have been proposed. However, these methods failed to reconstruct images…

Deep neural networks are a promising solution for applications that solve problems based on learning data sets. DNN accelerators solve the processing bottleneck as a domain-specific processor. Like other hardware solutions, there must be…

We address the challenge of applying existing convolutional neural network (CNN) architectures to compressed images. Existing CNN architectures represent images as a matrix of pixel intensities with a specified dimension; this desired…

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers…

Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promise in image classification tasks, its extension to other…

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly…

Spectral computed tomography (CT) has attracted much attention in radiation dose reduction, metal artifacts removal, tissue quantification and material discrimination. The x-ray energy spectrum is divided into several bins, each…

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet…

Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Current research on deep learning for medical image segmentation exposes their limitations in learning either global semantic information or local contextual information. To tackle these issues, a novel network named SegTransVAE is proposed…

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It…

Object rearranging is one of the most common deformable manipulation tasks, where the robot needs to rearrange a deformable object into a goal configuration. Previous studies focus on designing an expert system for each specific task by…