Images

ImageCLEF-DA

Introduced in Deep Transfer Learning with Joint Adaptation Networks2016

About this Dataset

The ImageCLEF-DA dataset is a benchmark dataset for ImageCLEF 2014 domain adaptation challenge, which contains three domains: Caltech-256 (C), ImageNet ILSVRC 2012 (I) and Pascal VOC 2012 (P). For each domain, there are 12 categories and 50 images in each category.

Source: Domain-Symmetric Networks for Adversarial Domain Adaptation Image Source: https://www.imageclef.org/2014/adaptation

Source: Deep Transfer Learning with Joint Adaptation Networks

Dataset Variants

ImageCLEF-DA

Papers1

Deep Transfer Learning with Joint Adaptation Networks

JAN is presented, which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion.

Tasks

EDIT

Domain Adaptation Multi-Source Unsupervised Domain Adaptation Scene Graph Detection Predicate Classification Scene Graph Classification

Similar Datasets