MIT-States Zero-Shot Learning Dataset
Date
3 years ago
Size
770.33 MB
Publish URL
Paper URL

MIT-States is a dataset for studying state transitions in image retrieval. The dataset contains 245 object classes (eg, fish, persimmon, room), 115 attributes (eg, mossy, deflated, dirty), and about 53,000 images.
On average each target instance was modified by 1 of the 9 provided attributes.
MIT-States.torrent
Seeding 1Downloading 0Completed 174Total Downloads 279
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp