-
Visual Concept Recognition and Localization via Iterative Introspection
The proposed method alternates classification and introspection. The introspection phase employs a strategy to select a sub-window for the next step by applying a beam-search to... -
Genetic Algorithm based hyper-parameters optimization for transfer Convolutio...
Hyperparameter optimization for transfer Convolutional Neural Networks (CNN) using Genetic Algorithm -
MPII Human Pose Dataset
Human pose estimation refers to the task of recognizing postures by localizing body keypoints (head, shoulders, elbows, wrists, knees, ankles, etc.) from images. -
SqueezeJet: High-level Synthesis Accelerator
Deep convolutional neural networks have dominated the pattern recognition scene by providing much more accurate solutions in computer vision problems such as object recognition... -
Visual Context-Aware Convolution Filters for Transformation-Invariant Neural ...
The proposed framework generates a unique set of context-dependent filters based on the input image, and combines them with max-pooling to produce transformation-invariant... -
Deep Epitomic Convolutional Neural Networks
Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new... -
Content-Aware Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution... -
Very Deep Convolutional Networks for Large-Scale Image Recognition
The dataset consists of 60,000 images of objects in 200 categories, with 300 images per category. -
PowerLinear Activation Functions with application to the first layer of CNNs
Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing. -
CIFAR100 and ImageNet
The dataset used in the paper is CIFAR100 and ImageNet. -
Group Equivariant Convolutional Networks
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting... -
Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels... -
ConvMLP: Hierarchical Convolutional MLPs for Vision
ConvMLP: a Hierarchical Convolutional MLP backbone for visual recognition -
Transform Quantization for CNN Compression
The dataset used in this paper is a collection of convolutional neural network (CNN) weights, which are compressed using transform quantization. -
CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation
Brain lesion segmentation provides a valuable tool for clinical diagnosis, and convolutional neural networks (CNNs) have achieved unprecedented success in the task. Data... -
FSCNN: A Fast Sparse Convolution Neural Network Inference System
Convolutional Neural Network (CNN) has demonstrated its success in plentiful computer vision application, but typically accompanies high computation cost and numerous redundant... -
Training Convolutional Networks with Web Images
This dataset is used to train a Convolutional Neural Network (CNN) to classify objects from web images. The dataset is created by downloading images from the web using a query... -
Container: A General-Purpose Building Block for Multi-Head Context Aggregation
Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers – originally introduced in...