Abstract: A method for scoring training data samples according to an ability to preserve latent decision boundaries for previously observed classes while promoting learning from an input batch of new images from an online data stream, comprising: receiving the input batch of the new images from the online data stream, performing a memory retrieval process that retrieves data to be learned along with a new set of data from the memory to retain the previously learned knowledge, and performing a memory update process that selects and exchanges a small set of data to be saved in the memory in the memory update process. In addition, the method performs data valuation based on KNN-SV for both the memory retrieval and memory update processes to perform strategic and intuitive data selection based on the properties of KNN-SV.

Abstract: A vision inspection device includes: a memory including a buffer; and a processor configured to: acquire a plurality of divided images by dividing a captured product image into a plurality of pieces and a new data set including new normal product type data and new defective type data corresponding to the plurality of divided images; sample at least one buffer data set among a plurality of buffer data sets stored in the buffer; generate a mini batch by combining the sampled buffer data set with the new data set; and determine whether to store the new data set in the buffer by using a soft nearest neighbor loss (SNNL) value of the new data set constituting the mini batch, and a cumulative average SNNL value of each of the buffer data sets constituting the mini batch.

Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.

Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.

Abstract: A method for scoring training data samples according to an ability to preserve latent decision boundaries for previously observed classes while promoting learning from an input batch of new images from an online data stream, comprising: receiving the input batch of the new images from the online data stream, performing a memory retrieval process that retrieves data to be learned along with a new set of data from the memory to retain the previously learned knowledge, and performing a memory update process that selects and exchanges a small set of data to be saved in the memory in the memory update process. In addition, the method performs data valuation based on KNN-SV for both the memory retrieval and memory update processes to perform strategic and intuitive data selection based on the properties of KNN-SV.