Author name cluster

Biswarup Bhattacharya

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2018 Short Paper

AdGAP: Advanced Global Average Pooling

Arna Ghosh
Biswarup Bhattacharya
Somnath Basu Roy Chowdhury

Global average pooling (GAP) has been used previously to generate class activation maps. The motivation behind AdGAP comes from the fact that the convolutional ﬁlters possess position information of the essential features and hence, combination of the feature maps could help us locate the class instances in an image. Our novel architecture generates promising results and unlike previous methods, the architecture is not sensitive to the size of the input image, thus promising wider application.

PDF Details

AAAI Conference 2018 Short Paper

Training Autoencoders in Sparse Domain

Biswarup Bhattacharya
Arna Ghosh
Somnath Basu Roy Chowdhury

Autoencoders (AE) are essential in learning representation of large data (like images) for dimensionality reduction. Images are converted to sparse domain using transforms like Fast Fourier Transform (FFT) or Discrete Cosine Transform (DCT) where information that requires encoding is minimal. By optimally selecting the feature-rich frequencies, we are able to learn the latent vectors more robustly. We successfully show enhanced performance of autoencoders in sparse domain for images.

PDF Details

AAAI Conference 2017 Short Paper

Handwriting Profiling Using Generative Adversarial Networks

Arna Ghosh
Biswarup Bhattacharya
Somnath Basu Roy Chowdhury

Handwriting is a skill learned by humans from a very early age. The ability to develop one’s own unique handwriting as well as mimic another person’s handwriting is a task learned by the brain with practice. This paper deals with this very problem where an intelligent system tries to learn the handwriting of an entity using Generative Adversarial Networks (GANs). We propose a modiﬁed architecture of DCGAN (Radford, Metz, and Chintala 2015) to achieve this. We also discuss about applying reinforcement learning techniques to achieve faster learning. Our algorithm hopes to give new insights in this area and its uses include identiﬁcation of forged documents, signature veriﬁcation, computer generated art, digitization of documents among others. Our early implementation of the algorithm illustrates a good performance with MNIST datasets.

PDF Details