Enregistré dans:
Détails bibliographiques
Auteurs principaux: Song, Ruizhuo, Yuan, Beiming
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.02688
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915551471730688
author Song, Ruizhuo
Yuan, Beiming
author_facet Song, Ruizhuo
Yuan, Beiming
contents Visual abstract reasoning is core to image processing. We present Valen, a unified probability-highlighting baseline that excels on both RPM (progression) and Bongard-Logo (clustering) tasks. Analysing its internals, we find solvers implicitly treat each task as a distribution where primary samples fit and auxiliaries do not; hence the learning target is jointly shaped by both sets, not by correct solutions alone. To close the gap we first introduce Tine, an adversarial adapter that nudges Valen toward correct-solution density, but adversarial training is unstable. We therefore replace it with Funny, a fast Gaussian-mixture model that directly estimates the correct-solution density without adversarial games, and extend the same paradigm to SBR for progressive-pattern planning. Extensive experiments show explicit distribution planning is the key to stronger, interpretable abstract reasoning. Codes are available in: https://github.com/Yuanbeiming/Funny-Valen-Tine-Planning-Solution-Distribution-Enhances-Machine-Abstract-Reasoning-Ability
format Preprint
id arxiv_https___arxiv_org_abs_2407_02688
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability
Song, Ruizhuo
Yuan, Beiming
Computer Vision and Pattern Recognition
Visual abstract reasoning is core to image processing. We present Valen, a unified probability-highlighting baseline that excels on both RPM (progression) and Bongard-Logo (clustering) tasks. Analysing its internals, we find solvers implicitly treat each task as a distribution where primary samples fit and auxiliaries do not; hence the learning target is jointly shaped by both sets, not by correct solutions alone. To close the gap we first introduce Tine, an adversarial adapter that nudges Valen toward correct-solution density, but adversarial training is unstable. We therefore replace it with Funny, a fast Gaussian-mixture model that directly estimates the correct-solution density without adversarial games, and extend the same paradigm to SBR for progressive-pattern planning. Extensive experiments show explicit distribution planning is the key to stronger, interpretable abstract reasoning. Codes are available in: https://github.com/Yuanbeiming/Funny-Valen-Tine-Planning-Solution-Distribution-Enhances-Machine-Abstract-Reasoning-Ability
title Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.02688