# Greedy Gradient Ensemble for Robust Visual Question Answering Source: [Greedy Gradient Ensemble for Robust Visual Question Answering]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:10:41.559Z Authors: Xinzhe Han, Shuhui Wang, Chi Su, Qingming Huang, Qi Tian Published: 2021-07-27T08:02:49.000Z ## Abstract Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information. As a result, they suffer from performance drop on out-of-distribution data and inadequate visual explanation. Based on experimental analysis for existing robust VQA methods, we stress the language bias in VQA that comes from two aspects, i.e., distribution bias and shortcut bias. We further propose a new de-bias framework, Greedy Gradient Ensemble (GGE), which combines multiple biased models for unbiased base model learning. With the greedy strategy, GGE forces the biased models to over-fit the biased data distribution in priority, thus makes the base model pay more attention to examples that are hard to solve by biased models. The experiments demonstrate that our method makes better use of visual information and achieves state-of-the-art performance on diagnosing dataset VQA-CP without using extra annotations. ## 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. - [Visual Question Answering on VQA-CP v2 (test)](): Visual Question Answering; VQA-CP v2 (test); Overall Accuracy: 57.32. - [Visual Question Answering on VQA v2 (val)](): Visual Question Answering; VQA v2 (val); Accuracy: 59.3. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()