Abstract: This disclosure relates generally to identification and mitigation of bias while training deep learning models. Conventional methods do not provide effective methods for bias identification, and they require pre-defined concepts and rules for bias mitigation. The embodiments of the present disclosure train an auto-encoder to produce a generalized representation of an input image by decomposing into a set of latent embedding. The set of latent embedding are used to learn the shape and color concepts of the input image. The feature specialization is done by training an auto-encoder to reconstruct the input image using the shape embedding modulated by color embedding. To identify the bias, permutation invariant neural network is trained for classification task and attribution scores corresponding to each concept embedding are computed. The method also performs de-biasing the classifier by training it with a set of counterfactual images generated by modifying the latent embedding learned by the auto-encoder.

Abstract: This disclosure relates generally to systems and methods for autonomous task composition of vision pipelines using an algorithm selection framework. The framework leverages transformer architecture along with deep reinforcement learning techniques to search an algorithmic space for unseen solution templates. In an embodiment, the present disclosure describes a two stage process of identifying the vision pipeline for a particular task. At first stage, a high-level sequence of the vision pipeline is provided by a symbolic planner to create the vision workflow. At second stage, suitable algorithms for each high-level task are selected. This is achieved by performing a graph search using a transformer architecture over an algorithmic space on each component of generated workflow. In order to make the system more robust, weights of embedding, key and query networks of a visual transformer are updated with a Deep Reinforcement Learning framework that uses Proximal Policy Optimization (PPO) as underlying algorithm.

Abstract: Conventional task planners assume that the task-plans provided are executable, hence these are not task-aware. Present disclosure alleviates the downward refinability assumption, that is, planning can be decomposed separate symbolic and continuous planning steps by introducing bi-level planning, a plan which is a series of actions that the robot needs to take to achieve the goal task is curated. Firstly, abstract symbolic actions are converted to continuous vectors and used therein to enable interaction with an environment. Images of objects placed in the environment are captured and concepts are learnt from the captured images and attributes of objects are detected. A hierarchical scene graph is generated from the concepts and attributes wherein the graph includes interpretable sub-symbolic representations and from these interpretable symbolic representations are obtained for identifying goal task.

Abstract: State of the art mechanisms being used for achieving diagnostic-quality images under low-dose settings for general CT imaging have the disadvantages that CT images are fixed during the optimization process to generate perfusion maps, which can lead to suboptimal CT images with respect to the perfusion maps generated, although they might appear spatially smooth or denoised. The disclosure herein generally relates to Computer Tomography (CT) scanning, and, more particularly, to a method and system for CT image reconstruction. The system performs modelling an optimization problem for joint estimation of a set of structural CT images and a perfusion map, and further solves the optimization problem for the reconstruction of the CT images of a subject.

Abstract: The disclosure herein relates to methods and systems for generating an end-to-end de-smoking model for removing smoke present in a video. Conventional data-driven based de-smoking approaches are limited mainly due to lack of suitable training data. Further, the conventional data-driven based de-smoking approaches are not end-to-end for removing the smoke present in the video. The de-smoking model of the present disclosure is trained end-to-end with the use of synthesized smoky video frames that are obtained by source aware smoke synthesis approach. The end-to-end de-smoking model localize and remove the smoke present in the video, using dynamic properties of the smoke. Hence the end-to-end de-smoking model simultaneously identifies the regions affected with the smoke and performs the de-smoking with minimal artifacts. localized smoke removal and color restoration of a real-time video.

Abstract: Automation is the key to build efficient workflows with minimum effort consumption. However, there is a large gap in workflow synthesis for automated AI application development. Computer vision workflow synthesis largely rely on domain expert due to lack of generalization over solution search space for given goal. This search space for creating suitable solution(s) using available algorithms is quite vast, which makes exploratory work of solution building a time-, effort- and intellect intensive endeavor. Embodiments of the present disclosure provide system and method for goal-driven algorithm selection approach for building computer vision workflows on the fly. The system generates one or more task workflows with associated success probability depending on initial conditions and input natural language goal query by combining various image processing algorithms. Symbolic AI planning is aided by Reinforcement Learning to recommend optimal workflows that are robust and adaptive to changes in the environment.

Abstract: The disclosure herein relates to methods and systems for localized smoke removal and color restoration of a real-time video. Conventional techniques apply the de-smoking process only on a single image, by finding the regions having the smoke, based on manual air-light estimation. In addition, regaining original colors of de-smoked image is quite challenging. The present disclosure herein solves the technical problems. In the first stage, video frames having the smoky and smoke-free video frames are identified, from the video received in the real-time. In the second stage, an air-light is estimated automatically using a combined feature map. An intermediate de-smoked video frame for each smoky video frame is generated based on the air-light using a de-smoking algorithm. In the third and the last stage, a smoke-free video reference frame is used to compensate for color distortions introduced by the de-smoking algorithm in the second stage.