24,175 datasets found

The CIFAR10 and CIFAR100 datasets are used to evaluate the proposed randomized defense method.

CIFAR10 and ImageNet datasets are used as the original task for the pre-trained models.

CIFAR10-C and ImageNet-C datasets are used to evaluate the proposed framework for improving the natural robustness of trained DNNs against corrupted inputs.

A dataset for training the ArtScore model

A dataset for training the ArtScore model

A dataset for training the ArtScore model

A dataset for evaluating the artness of AI-generated images

Ship orientation angle prediction (SOAP) with optical remote sensing images is an important image processing task, which often relies on deep convolutional neural networks...

The HKU dataset consists of 4447 images with multiple disconnected salient objects or objects touching the image boundary.

Feature matters for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered...

The proposed method for saliency detection task, which is composed of two main modules.

A large-scale point cloud classification benchmark, focusing on semantic segmentation of urban scenes.

Dataset of sound records from different points of the processing line in canteras

A deep learning approach for breast cancer detection on screening mammography.

A survey of the foundations, selected improvements, and some current applications of Deep Convolutional Neural Networks (CNNs).

3D-FRONT is a synthetic dataset composed of 6,813 houses with 14,629 rooms, where each room is arranged by a collection of high-quality 3D furniture objects from the 3D-FUTURE...

The datasets used in this paper are CelebA, LFWA, and RaFD.

MuST-C is a multilingual speech translation dataset, which contains at least 385 hours of audio recordings from TED Talks, with their manual transcriptions and translations at...

A benchmark dataset and evaluation methodology for video object segmentation.

Frozen in time: A joint video and image encoder for end-to-end retrieval.