Multiscale feature representations for object recognition and detection
AssigneeInternational Business Machines Corporation
InventorsQuanfu Fan, Richard Chen
Life of this patent
Estimating the term…
Abstract
Embodiments of the present invention are directed to a computer-implemented method for multiscale representation of input data. A non-limiting example of the computer-implemented method includes a processor receiving an original input. The processor downsamples the original input into a downscaled input. The processor runs a first convolutional neural network (“CNN”) on the downscaled input. The processor runs a second CNN on the original input, where the second CNN has fewer layers than the first CNN. The processor merges the output of the first CNN with the output of the second CNN and provides a result following the merging of the outputs.
Claims20
A computer-implemented method comprising:
- receiving, by a processor, an original input;
- downsampling, by the processor, the original input into a downscaled input;
- running, by the processor, a first convolutional neural network (“CNN”) on the downscaled input;
- running, by the processor, a second CNN on the original input, where the second CNN has fewer layers than the first CNN;
- merging, by the processor, the output of the first CNN with the output of the second CNN;
- and
- providing a result, by the processor, following the merging of the outputs.
A system comprising:
- a memory;
- a processor communicatively coupled to the memory, the processor operable to execute instructions stored in the memory, the instructions causing the processor to:
- receive an original input;
- downsample the original input into a downscaled input;
- run a first convolutional neural network (“CNN”) on the downscaled input;
- run a second CNN on the original input, where the second CNN has fewer layers than the first CNN;
- merge the output of the first CNN with the output of the second CNN;
- and
- provide a result following the merging of the outputs.
A computer program product for multiscale representation of image data, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer, to cause the computer to perform a method comprising:
- receiving, by a processor, an original input;
- downsampling, by the processor, the original input into a downscaled input;
- running, by the processor, a first convolutional neural network (“CNN”) on the downscaled input;
- running, by the processor, a second CNN on the original input, where the second CNN has fewer layers than the first CNN;
- merging, by the processor, the output of the first CNN with the output of the second CNN;
- and
- providing a result, by the processor, following the merging of the outputs.
Dependencies are inferred from the claim text.