这篇讲FISA，拿模型答错的题来造新训练图，比瞎做增强更准，还能和文本增强一起用。
FISA 框架从模型自身的失败案例中生成增强图像，避免使用与模型短板脱节的通用变换。该方法通过自检验和双重保真过滤，在保持答案正确的同时提升图像复杂度。在视觉问答基准上的实验表明，FISA 能持续改进分布内与分布外性能，并与现有文本自增强方法兼容。其合成样本的数据效率也优于通用图像增强基线。
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image augmentation remains underexplored and typically relies on generic or handcrafted transformations that are weakly aligned with the model's actual incapability. We propose Failure-informed Image Self-Augmentation (\textbf{FISA}), a framework for MLLM self-improvement that constructs augmented images from the model's own failure cases. Our method generates visually challenging yet answer-preserving image complications, verifies their utility through self-examination, and applies dual fidelity filtering to avoid semantic distortion. Experiments on visual question answering benchmarks show that the proposed method consistently improves performance across both in-distribution and out-of-distribution settings. Further experiments validate the compatibility of FISA with existing textual self-augmentation approaches, the superior data efficiency of the synthesized samples over generic image augmentation baselines, and the practical effectiveness of the proposed filtering strategy.