Omkar Thawakar's starred repositories
DiffusionDet
[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)
multimodal-prompt-learning
[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".
object-centric-ovd
[NeurIPS 2022] Official repository of paper titled "Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection".
Handwriting-Transformers
Handwriting-Transformers (ICCV21)
Open-World-Tracking
Official code for "Opening up Open World Tracking" (CVPR 2022)
doodleformer
DoodleFormer: Creative Sketch Drawing with Transformers (ECCV22)
data_science_interview
Interview questions asked in Data Science/ Machine Learning interviews
PS-ARM
Abstract. Person search is a challenging problem with various real- world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, previous study focuses on rich feature information learning, it’s still hard to re- trieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention- aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a per- son and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by intro- ducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervisions or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHK-SYSU [1] and PRW [2]. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5% in the mAP score over SeqNet, while operating at a comparable speed
Self-Learning-Robot
Reinforcement Training of Robot
NeuralNetwork
Implementation of Neural Network from scratch (from single continuous perceptron to multilayer neural network)
Reinforcement-Learning-Papers
All publications related to Reinforcement Learning and Deep reinforcement Learning
pix2pix-tensorflow
Easy to use general purpose implementation of pix2pix model in tensorflow to train for image to image translation
pix2pix-tensorflow
Separately Layerwise Weights assignment to Generator Network
TWO-GENERATOR-GAN
Background-Foreground Segmentation Recurrent GAN
2GEN_GAN-Tensorflow
2 Generator GAN network
OmkarThawakar.github.io
My Personal Website
self-learning-bot
A line follower bot which uses a Reinforcement Learning algorithm to learn to follow the line
ironman-svg-sketch
svg sketch of iron man.
Piston_Ring_Detection
Real time segmentation of piston ring
Remote-PC-Control
controlling the system remotely
my-IOS-app
IOS app using swift.
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
cvprlab_website
Django based website