Evaluating Motion Estimation Models from Behavioural and Psychophysical Data

Tlapale, Émilien; Kornprobst, Pierre; Bouecke, Jan D.; Neumann, Heiko; Masson, Guillaume S.

doi:10.1007/978-3-642-32615-8_46

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scoring such models might be challenging since the model design has often been guided by different goal specifications and task definitions. In Tlapale et al (2010) a first attempt was made to establish a test and evaluation strategy to conduct comparison studies for models of motion computation in biological and computational vision. Further, some of these authors suggest a task-centric framework for relating biological and computer vision in tasks which biological mechanisms face.…”

Section: Analyzing Vision At a Task-levelmentioning

confidence: 99%

Canonical circuit computations for computer vision

2023

View full text Add to dashboard Cite

Advanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advances in machine vision. We propose to utilize structural and functional principles of neural systems that have been largely overlooked. They potentially provide new inspirations for computer vision mechanisms and models. Recurrent feedforward, lateral, and feedback interactions characterize general principles underlying processing in mammals. We derive a formal specification of core computational motifs that utilize these principles. These are combined to define model mechanisms for visual shape and motion processing. We demonstrate how such a framework can be adopted to run on neuromorphic brain-inspired hardware platforms and can be extended to automatically adapt to environment statistics. We argue that the identified principles and their formalization inspires sophisticated computational mechanisms with improved explanatory scope. These and other elaborated, biologically inspired models can be employed to design computer vision solutions for different tasks and they can be used to advance neural network architectures of learning.

show abstract

Section: Analyzing Vision At a Task-levelmentioning

confidence: 99%