DeepAI AI Chat
Log In Sign Up

Negative Results in Computer Vision: A Perspective

by   Ali Borji, et al.
University of Central Florida

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.


page 1

page 2

page 3

page 4


Situated Cameras, Situated Knowledges: Towards an Egocentric Epistemology for Computer Vision

In her influential 1988 paper, Situated Knowledges, Donna Haraway uses v...

Addendum to Research MMMCV; A Man/Microbio/Megabio/Computer Vision

In October 2007, a Research Proposal for the University of Sydney, Austr...

When ChatGPT for Computer Vision Will Come? From 2D to 3D

ChatGPT and its improved variant GPT4 have revolutionized the NLP field ...

Does computer vision matter for action?

Computer vision produces representations of scene content. Much computer...

Computer Vision and Metrics Learning for Hypothesis Testing: An Application of Q-Q Plot for Normality Test

This paper proposes a new procedure to construct test statistics for hyp...

Visual Scene Representations: Contrast, Scaling and Occlusion

We study the structure of representations, defined as approximations of ...

Towards Better User Studies in Computer Graphics and Vision

Online crowdsourcing platforms make it easy to perform evaluations of al...