Multi-Image Visual Question Answering
While a lot of work has been done on developing models to tackle the problem of Visual Question Answering, the ability of these models to relate the question to the image features still remain less explored. We present an empirical study of different feature extraction methods with different loss functions. We propose New dataset for the task of Visual Question Answering with multiple image inputs having only one ground truth, and benchmark our results on them. Our final model utilising Resnet + RCNN image features and Bert embeddings, inspired from stacked attention network gives 39% word accuracy and 99% image accuracy on CLEVER+TinyImagenet dataset.
PDF AbstractCode
Visual Question Answering
Caltech-256
Visual Question Answering v2.0
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
1x1 Convolution •
Adam •
Attention Dropout •
Average Pooling •
Batch Normalization •
BERT •
Bottleneck Residual Block •
Convolution •
Dense Connections •
Dropout •
GELU •
Global Average Pooling •
Kaiming Initialization •
Layer Normalization •
Linear Layer •
Linear Warmup With Linear Decay •
Max Pooling •
Multi-Attention Network •
Multi-Head Attention •
ReLU •
Residual Block •
Residual Connection •
ResNet •
Scaled Dot-Product Attention •
Softmax •
Weight Decay •
WordPiece
