Aparna-B

academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

AVA-dataset-downloader

You may need these scripts to download AVA images from website.

bert_score

BERT score for text generation

BottleSum

Classification-of-digits-MNIST-

CNN-VIS

datasheet-for-dataset-template

Template for datasheet for datasets

illustration2vec

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Label-embeddings-in-image-classification

Convolutional Neural Networks (CNNs) are being widely used for various tasks in Computer Vision. We focus on the task of image classification particularly using CNNs with more focus on the relation or similarity between class labels. The similarity between labels is judged using label word embeddings and incorporated into the loss layer. We propose that shallower networks be learnt with more complex and structured losses, in order to gain from shorter training time and equivalent complexity. We train two variants of CNNs with multiple architectures , all limited to a maximum of ten convolution layers to obtain an accuracy of 93.27% on the Fashion-MNIST dataset and 86.40% on the CIFAR 10 dataset. We further probe the adversarial robustness of the model as well the classspecific behavior by visualizing the class confusion matrix.We also show some preliminary results towards extending a trained variant to zero-shot learning.

pyAudioAnalysis

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Aparna-B/pyAudioAnalysis

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Aparna-B/academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

Aparna-B/AVA-dataset-downloader

You may need these scripts to download AVA images from website.

Aparna-B/bert_score

BERT score for text generation

Aparna-B/BottleSum

Aparna-B/Classification-of-digits-MNIST-

Aparna-B/CNN-VIS

Aparna-B/datasheet-for-dataset-template

Template for datasheet for datasets

Aparna-B/illustration2vec

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Aparna-B/Label-embeddings-in-image-classification

Convolutional Neural Networks (CNNs) are being widely used for various tasks in Computer Vision. We focus on the task of image classification particularly using CNNs with more focus on the relation or similarity between class labels. The similarity between labels is judged using label word embeddings and incorporated into the loss layer. We propose that shallower networks be learnt with more complex and structured losses, in order to gain from shorter training time and equivalent complexity. We train two variants of CNNs with multiple architectures , all limited to a maximum of ten convolution layers to obtain an accuracy of 93.27% on the Fashion-MNIST dataset and 86.40% on the CIFAR 10 dataset. We further probe the adversarial robustness of the model as well the classspecific behavior by visualizing the class confusion matrix.We also show some preliminary results towards extending a trained variant to zero-shot learning.

Aparna-B/Aparna-B.github.io

Aparna-B/deform_conv_pytorch

PyTorch Implementation of Deformable Convolution

Aparna-B/DeformableConv

Aparna-B/diachronic-sense-modeling

Aparna-B/FairRankingRelevance

An examination of the role of relevance in fair exposure-based ranking

Aparna-B/German-Credit-classification

Aparna-B/HurtfulWords

Quantifying biases in BERT embeddings pretrained on MIMIC-III clinical notes

Aparna-B/JudgingNorms

An examination of data labeling practices for normative applications.

Aparna-B/lcifr

Learning Certified Individually Fair Representations

Aparna-B/lime-experiments

Code for all experiments.

Aparna-B/machine-learning-scripts

Collection of scripts and tools related to machine learning

Aparna-B/model-card-template

Template for model cards

Aparna-B/NeuroNER

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

Aparna-B/pvd_steganography

Python Implementation of Pixel Value Differencing based Steganography (LSB) - PNG Cover Images

Aparna-B/pygcn

Graph Convolutional Networks in PyTorch

Aparna-B/pytorch-CycleGAN-and-pix2pix

Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)

Aparna-B/pytorch-yolo2

Convert https://pjreddie.com/darknet/yolo/ into pytorch

Aparna-B/researcher

A jekyll based resume template

Aparna-B/transformer_rankers

A library to conduct ranking experiments with transformers.