Abstract: Provided are a method and apparatus for compressing a neural network model by using device characteristics. The method includes: obtaining the neural network model that is executed by a device; adjusting a target number of output channels of a target layer included in the neural network model, based on an arithmetic intensity obtained from a roofline model and a latency characteristic of a staircase pattern of the device; and compressing the neural network model such that the number of output channels of the target layer is equal to the adjusted target number of output channels.

Abstract: Provided is a quantization method of an artificial neural network model including a plurality of layers. The quantization method includes identifying an outlier from among activation elements output from a first layer among the layers of the artificial neural network model, determining and regularizing a weight to be regularized among weights applied to the first layer based on relevance with the identified outlier, and quantizing the artificial neural network model after the quantization.

Abstract: The method for adjusting a distortion of a field of view of a camera in an intelligent transportation system comprises: receiving a target image, generating a first extraction result by extracting a predefined target object within the target image and a second extraction result by extracting the target object within a reference image, determining whether a distortion of the field of view of the target camera exists, using a first comparison result between the first extraction result and the second extraction result and a predefined threshold, determining a distortion type of the field of view of the target camera, using the first comparison result, when the distortion of the field of view of the target camera exists, and adjusting the distortion of the field of view of the target camera by using a different field of view adjustment scheme according to the distortion type of the target camera.

Abstract: Provided is an inference method using a vision-language model (VLM). The VLM is pretrained to sequentially generate inference results for consecutive inputs according to an input prompt, and the inference method includes caching information associated with the input prompt acquired during an operation for generating a first inference result for a first input among the consecutive inputs to the VLM, maintaining the cached information after the first inference result is generated; and generating a second inference result for a second input following the first input among the consecutive inputs to the VLM, based on the cached information.

Abstract: Disclosed is a method for providing an alarm based on a behavior of a driver in a driver monitoring system. The method includes receiving a first image corresponding to the driver within a vehicle, generating first model output information which indicates possibility that an anomaly which compromises safety of the driver exists in the first image, from the first image, by using an artificial intelligence model. The method includes generating a first anomaly primary prediction result indicating whether the anomaly exists in the first image by comparing the first model output information with a first threshold, generating a first anomaly secondary prediction result by performing a first voting using the first anomaly primary prediction result and determining an anomaly alarm corresponding to the first image by performing a second voting using the first anomaly secondary prediction result.

Abstract: Disclosed are a method and system for changing a structure of a deep learning model based on a change in resolution of input data. The method of changing a structure of a deep learning model may include generating, by the at least one processor, a plurality of input data having different resolution by performing various resolution changes on input data having given resolution, performing, by the at least one processor, inference on each of the plurality of generated input data through a deep learning model, checking, by the at least one processor, the size of a feature map output by each of layers included in the deep learning model while the inference is performed, and changing, by the at least one processor, the structure of at least one of the layers based on the checked size of the feature map.

Abstract: According to an embodiment of the present disclosure, a method for providing an artificial intelligence-based model, performed by a computing device, is disclosed. The method includes providing a candidate model list comprising a plurality of candidate models which are artificial intelligence-based models. The method includes determining a target model to be converted or benchmarked, based on a first user input on the candidate model list. The method includes providing a candidate node list comprising a plurality of candidate nodes. The method includes determining a target node to be converted or benchmarked, based on a second user input on the candidate node list. The method includes converting the target model into a model supportable by the target node, based on information of the determined target model and information preset on the target node.

Abstract: Disclosed is a method and system for readjusting granularity of search results according to complexity of a query for generative search. An inference method may include extracting a length-by-length phrase from a document retrieved for a query of a user; determining a ranking of the length-by-length phrase in consideration of complexity of the query; and configuring a prompt for input to a generative language model based on the determined ranking. Here, the ranking of the length-by-length phrase may be determined such that a relatively long phrase has a higher ranking according to an increase in the complexity of the query.

Abstract: A method of compressing a neural network model for object recognition according to an embodiment of the present application includes: receiving an original model for object recognition trained based on a first data set; receiving a second data set of an analysis target; calculating object size information on sizes of objects included in an image of the second data set; performing pruning on at least one layer included in the original model based on the calculated object size information; and generating a compressed neural network model from the original model based on the results of performing the pruning.

Abstract: The effective network compression using simulation-guided iterative pruning according to various embodiments, can be configured so that, by means of an electronic device, a first neural network is pruned on the basis of a threshold value, a second neural network is generated, a gradient for each weighted value of the second neural network is calculated, and a third neural is acquired by applying the gradient to the first neural network.

Abstract: Provided are a method and apparatus for generating a safety control signal of a road. The method includes inputting road state information for a first time point, including a safety control signal for the first time point and dynamic information for the first time point obtained from a video of a road, to a prediction model, inferring dangerous situation prediction information for a second time point after the first time point, by using the prediction model, and generating a safety control signal notifying a risk of accident on the road for the second time point, based on the inferred dangerous situation prediction information, wherein the prediction model is trained by using a loss function configured by dangerous situation prediction information inferred for a specific time point from road state information before the specific time point, and dangerous situation measurement information calculated from road state information for the specific time point.

Abstract: Disclosed is a method and system for readjusting granularity of search results according to complexity of a query for generative search. An inference method may include extracting a length-by-length phrase from a document retrieved for a query of a user; determining a ranking of the length-by-length phrase in consideration of complexity of the query; and configuring a prompt for input to a generative language model based on the determined ranking. Here, the ranking of the length-by-length phrase may be determined such that a relatively long phrase has a higher ranking according to an increase in the complexity of the query.

Abstract: Disclosed are a method and apparatus for continuous authentication. An authentication method includes receiving image frames taken by a camera in succession, detecting a face area in the image frames, tracking a change in a location of the detected face area in the image frames, and performing continuous user authentication for the face area according to the change in the location by using the face area whose change in the location has been tracked and a deep learning model.

Abstract: Disclosed is a method and system for local compression of an artificial intelligence (AI) model. A local compression method for a model may include receiving a pretrained model as input; selecting a layer group as a portion of the input model; and partially compressing the selected layer group and retraining the compressed layer group, and the retraining of the compressed layer group may include retraining the compressed layer group based on input data and output data prestored for the selected layer group.

Abstract: Provided are methods and apparatuses for controlling traffic signals of traffic lights in a sub-area by using a neural network model. The method according to an embodiment of the present disclosure may configure state information of a sub-area by using downstream information obtained in a current cycle time for each of a plurality of intersections included in the sub-area. In addition, the method may input the state information to a trained reinforcement learning model, and obtain action information of the sub-area including green times and offsets, by using an output from the trained reinforcement learning model. Furthermore, the method may generate coordinated signal values for applying the action to traffic lights in the sub-area in a subsequent cycle time.

Abstract: Disclosed are a method and apparatus for real-time on-device authentication based on deep learning. A deep learning-based authentication method includes detecting a location of a region of interest (ROI) occupied by a face portion an input image by using a detection model, extracting a feature map from the input image by using a feature extractor of the detection model, extracting a fixed length feature for the face portion using the feature map and ROI pooling for the detected location of the ROI, and classifying a face included in the input image based on the fixed length feature.

Abstract: Provided are a method and apparatus for performing a convolution operation for optimizing the arithmetic intensity of device.

Abstract: Disclosed is a model compression method and system for compressing a model for optimizing to an equipment-friendly model. A model compression method may include acquiring criteria and sparsity for each filter of a model to which unstructured pruning is already applied, determining a filter for applying structured pruning among filters of the model based on the criteria and the sparsity, and applying the structured pruning to the model based on the determined filter.

Abstract: A method for compressing a neural network model is disclosed. The method for compressing a neural network model includes receiving, at a processor of the electronic apparatus, an original model including a plurality of layers each including a plurality of filters, a compression ratio to be applied to the original model, and a metric for determining an importance of the plurality of filters, determining the importance of the plurality of filters using the metric, normalizing the importance of the plurality of filters layer by layer, and compressing the original model by removing at least one filter among the plurality of filters based on the normalized importance and the compression ratio.

Abstract: Disclosed is a technology for de-identifying and restoring personal information in an image based on an encryption key. An image processing method for de-identifying and restoring image information, which is performed by an image processing system, may include detecting an object information area in image information, de-identifying the detected object information area by using an encryption key generated in relation to the detected object information area, and restoring the de-identified object information area by using the encryption key.