Abstract: A deep learning framework in continual learning that enforces consistency in predictions across time separated views and enables learning rich discriminative features for mitigating catastrophic forgetting in low buffer regimes. A deep-learning based computer-implemented method for continual learning over non-stationary data streams involves a number of sequential tasks (T) in which for each task (t) the method includes the steps of training a classification head with an objective function based on experience replay; and casting consistency regularization as an auxiliary self-supervised pretext-task.

Abstract: A computer-implemented method of synaptic consolidation for training a neural network using an episodic memory, and a semantic memory, by using a Fisher information matrix for estimating the importance of each synapse in the network to previous tasks of the neural network; evaluating the Fisher information matrix on the episodic memory using the semantic memory; adjusting the importance estimate such that functional integrity of the filters in the convolutional layers is maintained whereby the importance of each filter is given by the mean importance of its parameters; using the weights of the semantic memory as the anchor parameters for constraining an update of the synapses of the network based on the adjusted importance estimate; updating the semantic memory and fisher information matrix stochastically using exponential moving average, and interleaving samples from a current task with samples from the episodic memory for performing the training.

Abstract: An AI based change detection system for executing a method to detect changes in geo-tagged videos to update HD maps, the method employing a neural network of modular components including a keyframe extraction module for processing two or more videos relating to separate traversals of an area of interest to which the HD map which is to be updated relates, a deep neural network module processing output of the keyframe extraction module, a change detection module processing output of the deep neural network module, and an auxiliary computations module which is designed to aid the change detection module.

Abstract: A two-stage computer-implemented method for continual learning intertwining task-agnostic and task-specific learning whereby self-supervised training is followed by supervised learning for each task. To further restrict the deviation from the learned representations in the self-supervised stage, a task-agnostic auxiliary loss is employed during the supervised stage.

Abstract: A deep learning-based method for self-supervised online knowledge distillation to improve the representation quality of the smaller models in neural network. The method is completely self-supervised, i.e. knowledge is distilled during the pretraining stage in the absence of labels. Said method comprises the step of using a single-stage online knowledge distillation wherein at least two models collaboratively and simultaneously learn from each other.

Abstract: A computer-implemented method of self-supervised learning in neural network for scene understanding in autonomously moving vehicles wherein the method to estimate the ego-motion and the intrinsics (focal lengths and principal point) robustly in a unified manner from a pair of input overlapping images captured from a monocular camera, within a self-supervised monocular depth and ego-motion estimation problem by including multi-head self-attention modules within a transformer architecture.

Abstract: A Deep Learning based Multi-sensor Detection System for executing a method to process images from a visual sensor and from a thermal sensor for detection of objects in said images, wherein a first deep learning network for processing images from the visual sensor and a second deep learning network for pro-cessing images from the thermal sensor are jointly used and collaboratively trained for improving both networks ability to accurately detect said objects in said images.

Abstract: A computer implemented network for executing a self-supervised scene change detection method, wherein at least one image pair with images captured at different instances of time is processed to detect structural changes caused by an appearance or disappearance of an object in the image pair, and wherein a self-supervised pretraining method is employed that utilizes an unlabelled image pair or pairs to learn representations for scene change detection, and wherein the aligned image pair is subjected to a differencing based self-supervised pre-training method to maximize a correlation between changed regions in the images which provide the structural changes that occur in the image pairs.

Abstract: A semantic segmentation architecture comprising an asymmetric encoder—decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.

Abstract: Embodiments of the disclosure provide methods and systems for an artificial intelligence method of making predictions from a sequence of images. The method may include receiving the sequence of images acquired at different time points. The method may further include applying a stable model to process the sequence of images to make the predictions. The stable model is trained along with a working model and a plastic model. The training enforces a consistency among the working model, the stable model, and the plastic model. The working model is trained using a loss function including a cross-entropy loss on a union of a training batch and memory exemplars and a consistency loss on the memory exemplars.

Abstract: A semantic segmentation architecture comprising an asymmetric encoder-decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.

Abstract: A computer-implemented method to improve scale consistency and/or scale awareness in a model of self-supervised depth and ego-motion prediction neural networks processing a video stream of monocular images, wherein complementary GPS coordinates synchronized with the images are used to calculate a GPS to scale loss to enforce the scale-consistency and/or -awareness on the monocular self-supervised ego-motion and depth estimation. A relative weight assigned to the GPS to scale loss exponentially increases as training progresses. The depth and ego-motion prediction neural networks are trained using an appearance-based photometric loss between real and synthesized target images, as well as a smoothness loss on the depth predictions.

Abstract: A method and system for generating ground-truth annotations for object detection and classification for roadside objects in video data, wherein the method uses in combination an object detector to detect object instances of roadside objects in each frame of a video, a visual object tracker to detect and track the roadside object across the remaining video frames the roadside object appears in and clusters these detected object instances of the same roadside object into an object track, a trajectory analyzer to filter out object tracks that are unlikely from roadside objects, a classification model to classify each object instance in the object track into a predefined roadside object class, after which the object track as a whole is classified by seeking consensus among the individual object instance classifications in the object track, and classification consistency to determine whether the resulting roadside object class can be assigned automatically to the concerning object track as a ground-truth annotatio

Abstract: A computer-implemented method of training a computer-implemented deep neural network with a dataset with annotated labels, wherein at least two models are concurrently trained collaboratively, and wherein each model is trained with a supervised learning loss, and a mimicry loss in addition to the supervised learning loss, wherein the super-vised learning loss relates to learning from environmental cues and supervision from the mimicry loss relates to imitation in cultural learning.

Abstract: Real-time scene understanding system employing an object detection module with an algorithm for localization and classification of objects in an image, and a semantic segmentation module with an algorithm for classification of individual pixels in the image, wherein the system comprises an encoder module operable on an input image for the extraction of notable features in the input image, one or more attention modules to attribute among the notable features in the input image as provided by the encoder a relative contribution of each of such notable features in an output image to be reconstructed from the input image, and a decoder module for reconstructing the output image using the notable features, wherein the reconstructed output image is made available to the object detection module with the algorithm for localization and classification of objects in the image, and to the semantic segmentation module with the algorithm for classification of individual pixels in the image.

Abstract: Systems arranged to implement methods for positioning a semantic landmark in an image from the real world during a continuous motion of a monocular camera providing said image, using in combination image information from the camera and GPS information, wherein the camera parameters are unknown a priori and are estimated in a self-calibration step, wherein in a subsequent step positioning of the landmarks is completed using one of camera ego motion and depth estimation.

Abstract: A semantic segmentation architecture comprising an asymmetric encoder-decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.

Abstract: A method for training a robust deep neural network model in collaboration with a standard model in a minimax game in a closed learning loop. The method encourages the robust and standard models to align their feature spaces by utilizing the task-specific decision boundaries and explore the input space more broadly. The supervision from the standard model acts as a noise-free reference for regularizing the robust model. This effectively adds a prior on the learned representations which encourages the model to learn semantically relevant features which are less susceptible to off-manifold perturbations introduced by adversarial attacks. The adversarial examples are generated by identifying regions in the input space where the discrepancy between the robust and standard model is maximum within the perturbation bound. In the subsequent step, the discrepancy between the robust and standard models is minimized in addition to optimizing them on their respective tasks.

Abstract: Real-time scene understanding system employing an object detection module with an algorithm for localization and classification of objects in an image, and a semantic segmentation module with an algorithm for classification of individual pixels in the image, wherein the system comprises an encoder module operable on an input image for the extraction of notable features in the input image, one or more attention modules to attribute among the notable features in the input image as provided by the encoder a relative contribution of each of such notable features in an output image to be reconstructed from the input image, and a decoder module for reconstructing the output image using the notable features, wherein the reconstructed output image is made available to the object detection module with the algorithm for localization and classification of objects in the image, and to the semantic segmentation module with the algorithm for classification of individual pixels in the image.