Search Results for author: Bharath Bhushan Damodaran

Found 16 papers, 3 papers with code

Improved Positional Encoding for Implicit Neural Representation based Compact Data Representation

no code implementations10 Nov 2023 Bharath Bhushan Damodaran, Francois Schnitzler, Anne Lambert, Pierre Hellier

Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR).

Novel View Synthesis

Latent-Shift: Gradient of Entropy Helps Neural Codecs

no code implementations1 Aug 2023 Muhammet Balcilar, Bharath Bhushan Damodaran, Karam Naser, Franck Galpin, Pierre Hellier

End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts.

Decoder

RQAT-INR: Improved Implicit Neural Image Compression

no code implementations6 Mar 2023 Bharath Bhushan Damodaran, Muhammet Balcilar, Franck Galpin, Pierre Hellier

Deep variational autoencoders for image and video compression have gained significant attraction in the recent years, due to their potential to offer competitive or better compression rates compared to the decades long traditional codecs such as AVC, HEVC or VVC.

Image Compression Video Compression

Video Coding Using Learned Latent GAN Compression

no code implementations9 Jul 2022 Mustafa Shukor, Bharath Bhushan Damodaran, Xu Yao, Pierre Hellier

We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression.

Video Compression

Learning Perceptual Compression of Facial Video

no code implementations29 Sep 2021 Mustafa Shukor, Xu Yao, Bharath Bhushan Damodaran, Pierre Hellier

We leverage the generative capacity of GANs such as StyleGAN to represent and compress each video frame (intra compression), as well as the successive differences between frames (inter compression).

Video Compression

Semantic and Geometric Unfolding of StyleGAN Latent Space

no code implementations9 Jul 2021 Mustafa Shukor, Xu Yao, Bharath Bhushan Damodaran, Pierre Hellier

Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to a natural image.

Attribute Disentanglement +1

Wasserstein Adversarial Regularization (WAR) on label noise

1 code implementation8 Apr 2019 Kilian Fatras, Bharath Bhushan Damodaran, Sylvain Lobry, Rémi Flamary, Devis Tuia, Nicolas Courty

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping.

Semantic Segmentation

Randomized ICA and LDA Dimensionality Reduction Methods for Hyperspectral Image Classification

no code implementations19 Apr 2018 Chippy Jayaprakash, Bharath Bhushan Damodaran, Sowmya V, K. P. Soman

In literature a fewer number of pixels are randomly selected to partial to overcome this issue, however this sub-optimal strategy might neglect important information in the HSI.

Dimensionality Reduction General Classification +1

Fast Optimal Bandwidth Selection for RBF Kernel using Reproducing Kernel Hilbert Space Operators for Kernel Based Classifiers

no code implementations14 Apr 2018 Bharath Bhushan Damodaran

Thus, the objective of this letter is to propose an fast and efficient method to select the bandwidth parameter of the Gaussian kernel in the kernel based classification methods.

Classification General Classification

DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation

4 code implementations ECCV 2018 Bharath Bhushan Damodaran, Benjamin Kellenberger, Rémi Flamary, Devis Tuia, Nicolas Courty

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e. g. same classes), but also different latent data structures (e. g. different acquisition conditions).

Unsupervised Domain Adaptation

Data Dependent Kernel Approximation using Pseudo Random Fourier Features

no code implementations27 Nov 2017 Bharath Bhushan Damodaran, Nicolas Courty, Philippe-Henri Gosselin

Thus, reducing the number of feature dimensions is necessary to effectively scale to large datasets.

Large-Scale Optimal Transport and Mapping Estimation

2 code implementations7 Nov 2017 Vivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary, Nicolas Courty, Antoine Rolet, Mathieu Blondel

We prove two theoretical stability results of regularized OT which show that our estimations converge to the OT plan and Monge map between the underlying continuous measures.

Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.