most citedA Survey on Instance Segmentation: State of the art

501 citations · 522 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV20212 cited

SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images

Abdul Mueed Hafiz, Rouf Ul Alam Bhat, Shabir Ahmad Parah +1

3D model generation from single 2D RGB images is a challenging and actively researched computer vision task. Various techniques using conventional network architectures have been p…

cs.CV20215 cited

Attention mechanisms and deep learning for machine vision: A survey of the state of the art

Abdul Mueed Hafiz, Shabir Ahmad Parah, Rouf Ul Alam Bhat

With the advent of state of the art nature-inspired pure attention based models i.e. transformers, and their success in natural language processing (NLP), their extension to machin…

cs.CV20203 cited

Reinforcement Learning Based Handwritten Digit Recognition with Two-State Q-Learning

Abdul Mueed Hafiz, Ghulam Mohiuddin Bhat

We present a simple yet efficient Hybrid Classifier based on Deep Learning and Reinforcement Learning. Q-Learning is used with two Q-states and four actions. Conventional technique…

cs.CV20205 cited

Deep Network Ensemble Learning applied to Image Classification using CNN Trees

Abdul Mueed Hafiz, Ghulam Mohiuddin Bhat

Traditional machine learning approaches may fail to perform satisfactorily when dealing with complex data. In this context, the importance of data mining evolves w.r.t. building an…

cs.CV2020

Fast Training of Deep Networks with One-Class CNNs

Abdul Mueed Hafiz, Ghulam Mohiuddin Bhat

One-class CNNs have shown promise in novelty detection. However, very less work has been done on extending them to multiclass classification. The proposed approach is a viable effo…

cs.CV2020

Image Classification by Reinforcement Learning with Two-State Q-Learning

Abdul Mueed Hafiz

In this paper, a simple and efficient Hybrid Classifier is presented which is based on deep learning and reinforcement learning. Here, Q-Learning has been used with two states and…