PRISM: Progressive Reasoning through Iterative Slot Memory for Vision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ziyu, Han, Shuangpeng, Zhang, Mengmi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911731419185152
author Wang, Ziyu
Han, Shuangpeng
Zhang, Mengmi
author_facet Wang, Ziyu
Han, Shuangpeng
Zhang, Mengmi
contents Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete observations. Inspired by the iterative nature of human perception, we introduce PRISM (Progressive Reasoning through Iterative Slot Memory), a pyramid vision architecture that reasons over images through iterative refinement. At a high level, PRISM groups visual features into object-centric representations, retrieves relevant patterns from a learned memory, and iteratively refines the representation to resolve ambiguity and recover missing information. This organize-recall-refine process operates recurrently across multiple scales, enabling progressive improvement of visual representations. Across standard vision tasks, including image classification, object detection, and semantic segmentation, PRISM achieves competitive performance while demonstrating improved robustness under incomplete observations such as occlusion. These results suggest that iterative reasoning with structured representations and memory is a promising direction for building more resilient and adaptive vision models. Source code and models will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30942
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PRISM: Progressive Reasoning through Iterative Slot Memory for Vision
Wang, Ziyu
Han, Shuangpeng
Zhang, Mengmi
Computer Vision and Pattern Recognition
Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete observations. Inspired by the iterative nature of human perception, we introduce PRISM (Progressive Reasoning through Iterative Slot Memory), a pyramid vision architecture that reasons over images through iterative refinement. At a high level, PRISM groups visual features into object-centric representations, retrieves relevant patterns from a learned memory, and iteratively refines the representation to resolve ambiguity and recover missing information. This organize-recall-refine process operates recurrently across multiple scales, enabling progressive improvement of visual representations. Across standard vision tasks, including image classification, object detection, and semantic segmentation, PRISM achieves competitive performance while demonstrating improved robustness under incomplete observations such as occlusion. These results suggest that iterative reasoning with structured representations and memory is a promising direction for building more resilient and adaptive vision models. Source code and models will be released.
title PRISM: Progressive Reasoning through Iterative Slot Memory for Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30942