Related papers: Channel Scaling: A Scale-and-Select Approach for T…
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this CVPR 2015 paper, we discover that a high-quality visual saliency model can be trained with multiscale features…
Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices.…
In this paper, we explore the idea of weight sharing over multiple scales in convolutional networks. Inspired by traditional computer vision approaches, we share the weights of convolution kernels over different scales in the same layers of…
The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all layers is unfeasible…
Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larger networks or was…
Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…
Fetal head segmentation is a crucial step in measuring the fetal head circumference (HC) during gestation, an important biometric in obstetrics for monitoring fetal growth. However, manual biometry generation is time-consuming and results…
Convolutional Neural Networks (CNNs) are a standard approach for visual recognition due to their capacity to learn hierarchical representations from raw pixels. In practice, practitioners often choose among (i) training a compact custom CNN…
As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task. Existing model selection techniques are often constrained in their scope…
Although convolutional neural networks (CNNs) are now widely used in various computer vision applications, its huge resource demanding on parameter storage and computation makes the deployment on mobile and embedded devices difficult.…
Unsupervised pre-training and transfer learning are commonly used techniques to initialize training algorithms for neural networks, particularly in settings with limited labeled data. In this paper, we study the effects of unsupervised…
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…
Imaging through scattering is an important, yet challenging problem. Tremendous progress has been made by exploiting the deterministic input-output "transmission matrix" for a fixed medium. However, this "one-to-one" mapping is highly…
This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The core of such an approach is a loss function that…
We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…
Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity has led to performance improvements for various tasks.…
Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With…
We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…
Deepening and widening convolutional neural networks (CNNs) significantly increases the number of trainable weight parameters by adding more convolutional layers and feature maps per layer, respectively. By imposing inter- and intra-group…