SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11848 · 2020

Analysis of diversity-accuracy tradeoff in image captioning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We investigate the effect of different model architectures, training objectives, hyperparameter settings and decoding procedures on the diversity of automatically generated image captions. Our results show that 1) simple decoding by naive sampling, coupled with low temperature is a competitive and fast method to produce diverse and accurate caption sets; 2) training with CIDEr-based reward using Reinforcement learning harms the diversity properties of the resulting generator, which cannot be mitigated by manipulating decoding parameters. In addition, we propose a new metric AllSPICE for evaluating both accuracy and diversity of a set of captions by a single value.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.11848")
get_code_for_paper("2002.11848")
have("2002.11848")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2002.11848.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2002.11848.svg)](https://syntology.ai/paper/2002.11848)

Connect an agent — have() is free.