Due to the recent development in technologies and integration of millions of internet of thing’s devices, a lot of data is being generated everyday (known as Big Data, having 7 V’s like Volume, Velocity, Variety, Variability, Veracity, Visualization, and Value). This data required to be analysis for improving growth of several organizations/ applications like e-healthcare (i.e., for disease prediction), satellite (i.e., for weather prediction), etc. Together this, we are entering into an era of smart world, where Robotics is going to take place in most of the applications (to solve world’s problems). Implementing Robotics in applications like medical, automobile, etc., is an aim/ goal of computer vision. Computer Vision (CV) objective is fulfilled by several components like Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL). Apart from that, the need of reliable deep learning models is in applications like Colorization of Black and white images, Adding sounds to silent movies, automatic machine translation, object classification in photographs, automatic handwritten generation, character text generation, image caption generation, automatic game playing. Hence, Reliable Deep Learning methods for perception are highly effective for many tasks/ applications. However, in practice, it is unavoidable to encounter scenarios where the assumptions are violated: data may have different statistics during training and deployment, data may change over time, may contain noise, or there could even be adversarial attacks or critical issue or challenges which are require to be overcome. We are interested in investigating and guaranteeing deep leaning or deep neural networks model’s performance in several situations (applications). Hence, this (proposed) special issue will invite unpublished research articles which will cover all possible where deep learning can be used in possible areas (in near future).