Back to results
US 2024/0005628 A1Published application
Bidirectional compact deep fusion networks for multimodality visual analysis applications
AssigneeIntel Corporation
InventorsDongqi CAI, Anbang YAO, Yikai WANG, Ming LU, Yurong CHEN
Life of this patent
Estimating the term…
Abstract
Techniques related to bidirectional compact deep fusion networks for multimodal image inputs are discussed. Such techniques include applying a shared convolutional layer and independent batch normalization layers to input volumes for each modality and fusing features from the resultant output volumes in both directions across the modalities.
Claims21
1-25. (canceled)
A system comprising:
- a memory to store at least a portion of a first input volume corresponding to a first input image having a first modality and a portion of a second input volume corresponding to a second input image having a second modality, the first and second modalities providing different visual information for a same scene;
- and
- one or more processors coupled to the memory, the one or more processors to:
- apply a convolutional layer and a first batch normalization layer to the first input volume to generate a first output volume;
- apply the convolutional layer and a second batch normalization layer to the second input volume to generate a second output volume;
- and
- output a plurality of features corresponding to the first and second output volumes for the scene.
4 more elements
A method comprising:
- receiving a first input volume corresponding to a first input image having a first modality and a second input volume corresponding to a second input image having a second modality, the first and second modalities providing different visual information for a same scene;
- applying a convolutional layer and a first batch normalization layer to the first input volume to generate a first output volume;
- applying the convolutional layer and a second batch normalization layer to the second input volume to generate a second output volume;
- and
- outputting a plurality of features corresponding to the first and second output volumes for the scene.
2 more elements
At least one machine readable medium comprising a plurality of instructions that, in response to being executed on a device, cause the device to:
- receive a first input volume corresponding to a first input image having a first modality and a second input volume corresponding to a second input image having a second modality, the first and second modalities providing different visual information for a same scene;
- apply a convolutional layer and a first batch normalization layer to the first input volume to generate a first output volume;
- apply the convolutional layer and a second batch normalization layer to the second input volume to generate a second output volume;
- and
- output a plurality of features corresponding to the first and second output volumes for the scene.
2 more elements
Dependencies are inferred from the claim text.