48 datasets found

Groups: Object Detection Formats: JSON

Filter Results

  • COD10K

    The COD10K dataset is currently the largest challenging dataset for COD, containing 10K images with dense annotations.

  • COD10K, CHAMELEON, CAMO, ISTD, kvasir-SEG

    The dataset used for camouflaged object detection, shadow detection, and polyp segmentation tasks.

  • PASCAL Context

    The PASCAL Context dataset is a benchmark for multi-task learning in computer vision. It contains 10103 images with 5 tasks: semantic segmentation, human body part segmentation,...

  • LVIS-92i

    The LVIS-92i dataset contains 92 images with 92 object categories.

  • PACO-Part

    The PACO-Part dataset contains 59 images with 59 object categories.

  • PerSeg

    The PerSeg dataset contains 40 images with 40 object categories.

  • PASCAL

    A dataset of textual entailment tasks, used for evaluating the ability of language models to understand relationships between texts.

  • COCO validation dataset

    COCO validation dataset

  • COCO-20i

    Few-shot segmentation aims to segment novel classes by using the model trained on base classes.

  • PASCAL VOC 2007

    Multi-label image recognition is a practical and challenging task compared to single-label image classification.

  • PASCAL VOC2012

    Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.

  • RefCOCO

    The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

  • Cityscapes Panoptic Segmentation

    The Cityscapes dataset consists of 8 thing classes and 11 stuff classes.

  • NYUv2

    Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...

  • Coco: Common objects in context

    Publicly available plant image datasets are crucial in precision agriculture as they reduce the time and effort spent on data collection and preparation. Also, more data enable...

  • MS COCO 2014

    Vehicle detection in real-time is a challenging and important task. The existing real-time vehicle detection lacks accuracy and speed. Real-time systems must detect and locate...

  • Pascal VOC

    Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

  • SUN RGB-D

    RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained...

  • COCO Dataset

    The COCO dataset is a large-scale dataset for object detection, semantic segmentation, and captioning. It contains 80 object categories and 1,000 image instances per category,...

  • FSS-1000

    The FSS-1000 dataset contains 1000 images with 1000 object categories.