Abstract: A cache data compression method for a transformer-based neural network model and an electronic device for performing the same are provided. The cache data compression method includes obtaining a query tensor, a key tensor, and a value tensor corresponding to tokens, determining token importance for each of the tokens based on the query tensor and the key tensor, clustering the key tensor and the value tensor into a plurality of clusters based on the determined token importance, determining channel importance of channels included in at least one of the key tensor and the value tensor in each of the plurality of clusters, generating compressed key-value data by pruning at least one of the channels of the key tensor and the value tensor based on the determined channel importance, and storing the compressed key-value data as key-value cache data for the transformer-based neural network model.

Abstract: There is provided an electronic device and an operating method of the electronic device. The method includes generating a plurality of pieces of augmented position information for a first token input to a large language model (LLM) by augmenting position information of the first token, generating a plurality of queries for the first token based on the plurality of pieces of augmented position information, determining a plurality of first attention scores based on the plurality of queries, determining a first target attention score based on the plurality of first attention scores, and performing inference on the input based on the first target attention score.

Abstract: A method of compressing a large language model and an electronic device for performing the method are provided. A method of operating an electronic device includes receiving data by a neural network model including at least one transformer block and at least one operation block, and outputting an inference result for the data in the neural network model. The at least one operation block is configured to receive tokens generated based on the data as an input, and selectively perform an operation on at least one of the tokens based on an index of the tokens.

Abstract: An operating method of an electronic device includes inputting a plurality of tokens into a first language model (LM) trained to omit performing an operation of a first operation block on first tokens of the plurality of tokens, and generating, by the first LM, an output corresponding to the plurality of tokens by performing inference on the plurality of tokens. The generating of the output corresponding to the plurality of tokens includes inputting the plurality of tokens into a target transformer block of the first LM, determining the first tokens at a pruning ratio at which the operation of the first operation block is omitted, based on a similarity of the plurality of tokens, inputting, into the first operation block, second tokens of the plurality of tokens excluding the first tokens, and bypassing the first tokens to a next operation block of the first operation block.

Abstract: An apparatus with region of interest (ROI) extraction includes: a processor configured to: generate an input image by distorting an original image comprising one or more objects; determine, based on the original image, a quality score of the input image using a machine learning model that is trained based on a mean opinion score (MOS) dataset; generate a class activation map for the input image based on the quality score of the input image; and extract an ROI from the original image based on the class activation map.

Abstract: Disclosed are a method and apparatus for training a neural network model to increase performance of the neural network model, the method including receiving input data and target data, pooling, by a neural network model, on a feature map extracted from the input data based on a probability for each of classes of the feature map, generating output data by inputting the input data to a neural network model, determining a loss based on comparing the output data and the target data and an auxiliary loss of the pooling, and training the neural network model based on the loss.

Abstract: An apparatus with region of interest (ROI) extraction includes: a processor configured to: generate an input image by distorting an original image comprising one or more objects; determine, based on the original image, a quality score of the input image using a machine learning model that is trained based on a mean opinion score (MOS) dataset; generate a class activation map for the input image based on the quality score of the input image; and extract an ROI from the original image based on the class activation map.

Abstract: An electronic device and method for detecting contamination of a camera lens, where the electronic device includes at least one camera configured to capture an image, a memory configured to store the image, and a contamination detection model configured to detect a contaminated portion of a lens of the at least one camera, in response to the image being input, and a processor configured to determine whether an operation of the electronic device is hindered by the contaminated portion, in response to the contamination detection model detecting the contaminated portion in the lens of the at least one camera.

Abstract: Disclosed are a method and apparatus for training a neural network model to increase performance of the neural network model, the method including receiving input data and target data, pooling, by a neural network model, on a feature map extracted from the input data based on a probability for each of classes of the feature map, generating output data by inputting the input data to a neural network model, determining a loss based on comparing the output data and the target data and an auxiliary loss of the pooling, and training the neural network model based on the loss.