Semi Supervised Learning for Image Captioning

2 papers with code • 3 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

Benchmarks

Add a Result

These leaderboards are used to track progress in Semi Supervised Learning for Image Captioning

Dataset	Best Model	Compare
MS COCO	Perturb, Predict & Paraphrase	See all
Flickr30k	CapDec	See all
FlickrStyle10K	CapDec	See all

Datasets

Subtasks

Pseudo Label

Most implemented papers

Most implemented Social Latest No code

Text-Only Training for Image Captioning using Noise-Injected CLIP

davidhuji/capdec • • 1 Nov 2022

We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images.

Paper
Code

Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning

csalt-research/perturb-predict-paraphrase • • IJCAI 2021

The original algorithm relies on computationally expensive data augmentation steps that involve perturbing the raw images and computing features for each perturbed image.