# Champion Solution for the WSDM2023 Toloka VQA Challenge

Source: [Champion Solution for the WSDM2023 Toloka VQA Challenge](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a4f>)

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

Data updated: 2025-10-26T01:00:51.913Z

Authors: Shengyi Gao, Zhe Chen, Guo Chen, Wenhai Wang, Tong Lu

Published: 2023-01-22T03:14:31.000Z

## Abstract

In this report, we present our champion solution to the WSDM2023 Toloka Visual Question Answering (VQA) Challenge. Different from the common VQA and visual grounding (VG) tasks, this challenge involves a more complex scenario, i.e. inferring and locating the object implicitly specified by the given interrogative question. For this task, we leverage ViT-Adapter, a pre-training-free adapter network, to adapt multi-modal pre-trained Uni-Perceiver for better cross-modal localization. Our method ranks first on the leaderboard, achieving 77.5 and 76.347 IoU on public and private test sets, respectively. It shows that ViT-Adapter is also an effective paradigm for adapting the unified perception model to vision-language downstream tasks. Code and models will be released at https://github.com/czczup/ViT-Adapter/tree/main/wsdm2023.

## 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/2301.09045>)

[PDF](<https://arxiv.org/pdf/2301.09045.pdf>)
