# Alleviating Noisy Data in Image Captioning with Cooperative Distillation

Source: [Alleviating Noisy Data in Image Captioning with Cooperative Distillation](<https://www.sota2.com/research/paper/68fa68fe1e209131cea1fa8d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:51:52.067Z

Authors: Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff

Published: 2020-12-21T21:32:28.000Z

## Abstract

Image captioning systems have made substantial progress, largely due to the availability of curated datasets like Microsoft COCO or Vizwiz that have accurate descriptions of their corresponding images. Unfortunately, scarce availability of such cleanly labeled data results in trained algorithms producing captions that can be terse and idiosyncratically specific to details in the image. We propose a new technique, cooperative distillation that combines clean curated datasets with the web-scale automatically extracted captions of the Google Conceptual Captions dataset (GCC), which can have poor descriptions of images, but is abundant in size and therefore provides a rich vocabulary resulting in more expressive captions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.11691>)

[PDF](<https://arxiv.org/pdf/2012.11691.pdf>)