660 datasets found

The dataset used for the experiments of the paper "CORE-PERIPHERY PRINCIPLE GUIDED REDISIGN OF SELF-ATTENTION IN TRANSFORMERS"

VisDA-C is a dataset for visual domain adaptation, consisting of synthetic rendering of 3D models in the source domain and Microsoft COCO real images in the target domain.

The dataset introduced in [17] and [18] was used to evaluate the performance of CrystalNet.

The dataset used in this work consisted of 486,000 protein crystallography X-ray images.

The dataset used in the paper is a multi-graph problem, where each graph represents a different network. The dataset is used to evaluate the performance of the RECS algorithm on...

Image classification is a fundamental task in computer vision, and the quest to enhance DNN accuracy without inflating model size or latency remains a pressing concern.

CIFAR-10 image classification using feature ensembles

The ImageNet-1k dataset is used as the backbone network for the proposed DEYOv2 model.

The CrowdHuman validation dataset contains 4370 images of people in highly crowded settings.

The MS COCO mini-val dataset contains 5000 images of 80 classes.

The street view house number recognition task involves transcribing an image with house numbers to a string of digits.

The dataset used in the paper is CIFAR-100 and SVHN, which are image classification datasets.

The dataset used in the paper is a binary image classification dataset, containing images of size 2x2, 4x4, and 8x8.

The dataset used in the paper is Places, a large dataset of 400k pairs of images from the Places 205 dataset and corresponding spoken audio captions.

The proposed framework for image classification tasks, using a hypersphere representation of deep features.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors pre-trained GANs on four datasets: MNIST, Fashion-MNIST, CIFAR-10, and CelebA.

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade...

The dataset used in the paper is ImageNet V2, a large-scale image classification dataset.

The ILSVRC 2012 classification challenge dataset was used to evaluate the proposed method.

The dataset used in this paper is the ConvNeXt-T and ConvNeXt-S datasets, which are variants of the ConvNeXt model.