# Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning

Source: [Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning](<https://www.sota2.com/research/paper/68fa78a11e209131cea79748>)

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

Data updated: 2025-10-26T04:43:14.257Z

Authors: Neha Kalibhat, Priyatham Kattakinda, Sumit Nawathe, Arman Zarei, Nikita Seleznev, Samuel Sharpe, Senthil Kumar, Soheil Feizi

Published: 2024-05-26T01:46:22.000Z

## Abstract

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from visual data. This paper explores the notion of providing semantically-meaningful visual tokens to transformer encoders within a vision-language pre-training framework. Leveraging off-the-shelf segmentation and scene-graph models, we extract representations of instance segmentation masks (referred to as tangible tokens) and relationships and actions (referred to as intangible tokens). Subsequently, we pre-train a vision-side transformer by incorporating these newly extracted tokens and aligning the resultant embeddings with caption embeddings from a text-side encoder. To capture the structural and semantic relationships among visual tokens, we introduce additive attention weights, which are used to compute self-attention scores. Our experiments on COCO demonstrate notable improvements over ViTs in learned representation quality across text-to-image (+47%) and image-to-text retrieval (+44%) tasks. Furthermore, we showcase the advantages on compositionality benchmarks such as ARO (+18%) and Winoground (+10%).

## 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/2405.16401>)

[PDF](<https://arxiv.org/pdf/2405.16401.pdf>)