Counterfactual samples synthesizing and training for robust visual question answering
Today's VQA models still tend to capture superficial linguistic correlations in the training set and fail to generalize to the test set with different QA distributions. To reduce these language biases, recent VQA works introduce an auxiliary question-only model to regularize the training of tar...
Saved in:
Main Authors: | , , , , |
---|---|
其他作者: | |
格式: | Article |
語言: | English |
出版: |
2023
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/171830 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |