# Negative Results in Computer Vision: A Perspective

## TL;DR

This paper emphasizes the importance of negative results in computer vision, discussing how they can be better disseminated and learned from to improve scientific rigor and progress in the field.

## Contribution

It highlights the value of negative results in computer vision, proposing strategies for their dissemination and discussing lessons from cognitive vision research.

## Key findings

- Negative results are undervalued in computer vision research.
- Disseminating negative results can improve experimental rigor.
- Lessons from cognitive vision can inform better research practices.

## Abstract

A negative result is when the outcome of an experiment or a model is not what is expected or when a hypothesis does not hold. Despite being often overlooked in the scientific community, negative results are results and they carry value. While this topic has been extensively discussed in other fields such as social sciences and biosciences, less attention has been paid to it in the computer vision community. The unique characteristics of computer vision, particularly its experimental aspect, call for a special treatment of this matter. In this paper, I will address what makes negative results important, how they should be disseminated and incentivized, and what lessons can be learned from cognitive vision research in this regard. Further, I will discuss issues such as computer vision and human vision interaction, experimental design and statistical hypothesis testing, explanatory versus predictive modeling, performance evaluation, model comparison, as well as computer vision research culture.