Method and apparatus for context-embedding and region-based object detection

A non-transitory computer-readable medium comprising program instructions for causing an apparatus to perform at least the following:

• generating, by a convolutional neural network (CNN), a plurality of reference feature maps based on an image that includes an object;
• generating a feature pyramid including a plurality of final feature maps corresponding, respectively, to the plurality of reference feature maps, wherein respective ones of the plurality of final feature maps are associated with different levels of the feature pyramid;
• obtaining a proposed region of interest (ROI);
• generating at least a first context ROI based on the proposed ROI such that an area of the first context ROI is larger than an area of the proposed ROI;
• assigning the proposed ROI to a first final feature map, associated with one level of the different levels of the feature pyramid, from among the plurality of final feature maps;
• assigning the first context ROI to a second final feature map, associated with another level of the different levels of the feature pyramid, from among the plurality of final feature maps, a size of the first final feature map being different than a size of the second final feature map;
• extracting a first set of features from the first final feature map associated with the one level of the different levels of the feature pyramid by performing an ROI pooling operation on the first final feature map using the proposed ROI;
• extracting a second set of features from the second final feature map associated with the other level of the different levels of the feature pyramid by performing an ROI pooling operation on the second final feature map using the first context ROI;
• applying a concatenation of the first set of features and the second set of features to a squeeze-and-excitation block (SEB);
• and
• determining, based on an output of the SEB, one or more probability values associated with a location of the object with respect to the image and a class of the object.

An apparatus comprising:

• at least one processor;
• and
• at least one memory including computer program code,
• the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
• generating, by a convolutional neural network (CNN), a plurality of reference feature maps based on an image that includes an object;
• generating a feature pyramid including a plurality of final feature maps corresponding, respectively, to the plurality of reference feature maps, wherein respective ones of the plurality of final feature maps are associated with different levels of the feature pyramid;
• obtaining a proposed region of interest (ROI);
• generating at least a first context ROI based on the proposed ROI such that an area of the first context ROI is larger than an area of the proposed ROI;
• assigning the proposed ROI to a first final feature map, associated with one level of the different levels of the feature pyramid, from among the plurality of final feature maps;
• assigning the first context ROI to a second final feature map, associated with another level of the different levels of the feature pyramid, from among the plurality of final feature maps, a size of the first final feature map being different than a size of the second final feature map;
• extracting a first set of features from the first final feature map associated with the one level of the different levels of the feature pyramid by performing an ROI pooling operation on the first final feature map using the proposed ROI;
• extracting a second set of features from the second final feature map associated with the other level of the different levels of the feature pyramid by performing an ROI pooling operation on the second final feature map using the first context ROI;
• applying a concatenation of the first set of features and the second set of features to a squeeze-and-excitation block (SEB);
• and
• determining, based on an output of the SEB, one or more probability values associated with a location of the object with respect to the image and a class of the object.