# From seeing to remembering: Images with harder-to-reconstruct representations leave stronger memory traces

arXiv: https://arxiv.org/abs/2302.10392 · HTML: https://mlsanity.com/paper/2302.10392/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 62 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Builds on (most cited first, 3 of 3)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [On the relationship between predictive coding and backpropagation](https://mlsanity.com/paper/2106.13082/) (2021)
- [The Resiliency of Memorability: A Predictor of Memory Separate from Attention and Priming](https://mlsanity.com/paper/1703.07738/) (2017)

## Built on by (most cited first, 1 of 1)

- [Modeling Visual Memorability Assessment with Autoencoders Reveals Characteristics of Memorable Images](https://mlsanity.com/paper/2410.15235/) (2024)

## Abstract (arXiv)

Much of what we remember is not due to intentional selection, but simply a by-product of perceiving. This raises a foundational question about the architecture of the mind: How does perception interface with and influence memory? Here, inspired by a classic proposal relating perceptual processing to memory durability, the level-of-processing theory, we present a sparse coding model for compressing feature embeddings of images, and show that the reconstruction residuals from this model predict how well images are encoded into memory. In an open memorability dataset of scene images, we show that reconstruction error not only explains memory accuracy but also response latencies during retrieval, subsuming, in the latter case, all of the variance explained by powerful vision-only models. We also confirm a prediction of this account with 'model-driven psychophysics'. This work establishes reconstruction error as a novel signal interfacing perception and memory, possibly through adaptive modulation of perceptual processing.