Related papers: Path-Level Network Transformation for Efficient Ar…

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators to form high-performance hybrid visual architectures still…

Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that…

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate…

The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently. Typically, such architectures have been handcrafted in the literature. However, given the size and…

The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture…

General graphs are difficult for learning due to their irregular structures. Existing works employ message passing along graph edges to extract local patterns using customized graph kernels, but few of them are effective for the integration…

Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…

The performance of convolutional neural networks (CNN) depends heavily on their architectures. Transfer learning performance of a CNN relies quite strongly on selection of its trainable layers. Selecting the most effective update layers for…

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require…

We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on…

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…

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…

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To…

Efficient and fast reconstruction of anatomical structures plays a crucial role in clinical practice. Minimizing retrieval and processing times not only potentially enhances swift response and decision-making in critical scenarios but also…

Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on…

Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g.,…

We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…

Meta-learning is a line of research that develops the ability to leverage past experiences to efficiently solve new learning problems. Meta-Reinforcement Learning (meta-RL) methods demonstrate a capability to learn behaviors that…

Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications…

Reconstructing Portal Vein and Hepatic Vein trees from contrast enhanced abdominal CT scans is a prerequisite for preoperative liver surgery simulation. Existing deep learning based methods treat vascular tree reconstruction as a semantic…