soumya1612-rasha Goto Github PK

clip

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

cmsc828a-spring2023

Repository for delivering programming assignment course materials for the Spring 2023 offering of CMSC828A “Fantastic Machine Learning Paradigms and Where to use Them” taught by Tianyi Zhou and TA'd by John Kirchenbauer, Maharshi Gor, and Kwesi Cobbina at University of Maryland, College Park.

cnc_ood

[ECML 2022] Official code for the paper "A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions"

group_dro

Distributionally robust neural networks for group shifts

handwritten_character_recogniser_rasha

homepage_website

Source code for personal home page

homework1

image-captioning

Attention based Image Caption Generator

informative-outlier-mining

We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.

keras-gan_rasha

Implementation of Semi-Supervised Generative Adversarial Network

missing-semester

The Missing Semester of Your CS Education 📚

odin

A simple and effective method for detecting out-of-distribution images in neural networks.

resco-cc

This repository is the implementation of the paper ReSCo-CC: Unsupervised Identification of Key Disinformation Sentences

show-attend-and-tell

[Python 3] Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"

smartparkingproject

soumya

Webpage of Soumya Suvra Ghosal

spurious_ood

starter-hugo-academic

summarization-sing-pair-mix

Code, Models, and Data for the ACL 2019 paper "Scoring Sentence Singletons and Pairs for Abstractive Summarization"

traveltimeprediction_tensorfactorization_uberdata

It modifies the Uber GPS data given by Uber black cab pickups in San Francisco and passes it to an algorithm for applying tensor decomposition algorithm(Tucker Decomposition) to find missing values. Any given query path is passed to the above algorithm and it finds the travel time for it.

vit-spurious-robustness