BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

31 Jan 2019  ·  Hedi Ben-Younes, Rémi Cadene, Nicolas Thome, Matthieu Cord ·

Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows quadratically with the input dimensions, making their practical implementation within classical deep learning pipelines challenging. In this paper, we introduce BLOCK, a new multimodal fusion based on the block-superdiagonal tensor decomposition. It leverages the notion of block-term ranks, which generalizes both concepts of rank and mode ranks for tensors, already used for multimodal fusion. It allows to define new ways for optimizing the tradeoff between the expressiveness and complexity of the fusion model, and is able to represent very fine interactions between modalities while maintaining powerful mono-modal representations. We demonstrate the practical interest of our fusion model by using BLOCK for two challenging tasks: Visual Question Answering (VQA) and Visual Relationship Detection (VRD), where we design end-to-end learnable architectures for representing relevant interactions between modalities. Through extensive experiments, we show that BLOCK compares favorably with respect to state-of-the-art multimodal fusion models for both VQA and VRD tasks. Our code is available at https://github.com/Cadene/block.bootstrap.pytorch.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Question Answering (VQA) VQA v2 test-dev BLOCK Accuracy 67.58 # 39
Visual Question Answering (VQA) VQA v2 test-std BLOCK overall 67.9 # 34
Visual Relationship Detection VRD Phrase Detection BLOCK R@100 28.96 # 2
R@50 26.32 # 1
Visual Relationship Detection VRD Predicate Detection BLOCK R@100 92.58 # 3
R@50 86.58 # 1
Visual Relationship Detection VRD Relationship Detection BLOCK R@100 20.96 # 3
R@50 19.06 # 2

Methods


No methods listed for this paper. Add relevant methods here