# Seeing in Words: Learning to Classify through Language Bottlenecks

Source: [Seeing in Words: Learning to Classify through Language Bottlenecks](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fd1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:29:17.533Z

Authors: Khalid Saifullah, Yuxin Wen, Jonas Geiping, Micah Goldblum, Tom Goldstein

Published: 2023-06-29T00:24:42.000Z

## Abstract

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability into neural networks, we train a vision model whose feature representations are text. We show that such a model can effectively classify ImageNet images, and we discuss the challenges we encountered when training it.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.00028>)

[PDF](<https://arxiv.org/pdf/2307.00028.pdf>)