# Visual Grounding Methods for VQA are Working for the Wrong Reasons!

Source: [Visual Grounding Methods for VQA are Working for the Wrong Reasons!](<https://www.sota2.com/research/paper/68fa72fb1e209131cea59c43>)

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

Data updated: 2025-10-26T02:39:34.909Z

Authors: Robik Shrestha, Kushal Kafle, Christopher Kanan

Published: 2020-04-12T21:45:23.000Z

## Abstract

Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons. To address this issue, recent bias mitigation methods for VQA propose to incorporate visual cues (e.g., human attention maps) to better ground the VQA models, showcasing impressive gains. However, we show that the performance improvements are not a result of improved visual grounding, but a regularization effect which prevents over-fitting to linguistic priors. For instance, we find that it is not actually necessary to provide proper, human-based cues; random, insensible cues also result in similar improvements. Based on this observation, we propose a simpler regularization scheme that does not require any external annotations and yet achieves near state-of-the-art performance on VQA-CPv2.

## 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/2004.05704>)

[PDF](<https://arxiv.org/pdf/2004.05704.pdf>)
