bhavinjawade

MLToolkit

Made@UB - MLToolkit is a visual framework for quick ML prototyping.

ProxyFusion-NeurIPS

Codebase for NeurIPS 2024 - ProxyFusion: Face Feature Aggregation Through Sparse Experts

CollegeFestWebsite

Official College Fest Website of AAYAAM (SGSITS) 2018.

RidgeBase_Fingerprint_Camera_App

Awesome-PEFT

A currated list of papers, blogs and codes for parameter efficient finetuning

bhavinjawade.github.io

My personal website with blogs

Contactless-Fingerprint-Gradio-Demo

Contactless Fingerprint Gradio Demo

NAPReq

Code for "NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings", WACV 2023 Paper.

SCC-Camera-App

NSF SCC-PG UB - Image Collection App and Model

ai_on_threads

allaboutwordsJM

ast

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

audio-text_retrieval

Implementation of our paper 'On Metric Learning For Audio-Text Cross-Modal Retrieval'

bhavinjawade

Calorie

Stupendously Stupid Calorie Tracker

cheer_demo

CNN-for-Raw-Waveforms

This is my PyTorch implementation of the "Very Deep Convolutional Neural Networks For Raw Waveforms" research paper published in 2016.

DeepSeek-V3

github-markdown-css

The minimal amount of CSS to replicate the GitHub Markdown style

LDAM-DRW

[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

personal

personal website new

PiCO

PyTorch implementation of PiCO https://arxiv.org/abs/2201.08984

proxyfusion_ub

proxyfusion_project_webpage

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

RidgeBase

RidgeBase: A Cross-Sensor Multi-Finger Contactless Fingerprint Dataset

rince

This is the code accompanying the AAAI 2022 paper "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" https://arxiv.org/abs/2201.11736 . The method allows you to use additional ranking information for representation learning.

SCOT

SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

TinyImageNet-Transformers

Transformers trained on Tiny ImageNet

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch