Mehul Kumar's Projects
Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere".
CNN Based Autoencoder Application in Breast Cancer Image Retrieval 🔬
The official implementation of CMAE https://arxiv.org/abs/2207.13532 and https://ieeexplore.ieee.org/document/10330745
CMAEH: Contrastive masked autoencoder based hashing for efficient image retrieval
Implementation of Some Deep Hash Algorithms, Including DPSH、DSH、DHN、HashNet、DSDH、DTSH、DFH、GreedyHash、CSQ.
Program for generating synthetic raindrops on real images. Used for generating datasets for the paper "Adherent Raindrop Removal with Self-Supervised Attention Maps and Spatio-Temporal Generative Adversarial Networks."
DIP Assignment
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
Face Transformer for Recognition
[NeurIPS 2021] Global Filter Networks for Image Classification
Code release for "HashNet: Deep Learning to Hash by Continuation" (ICCV 2017)
Official implementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".
Config files for my GitHub profile.
[Preprint] Neighborhood Attention Transformer, 2022
NAT implementation(Neighborhood Attention Transformer) This is an unofficial implementation. https://arxiv.org/pdf/2204.07143.pdf
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
[ICLR2022] official implementation of UniFormer
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Vision Transformer Hashing (VTS) utilizes the Vision Transformer to generate the hash code for image retrieval. It is tested under different retrieval frameworks such as DSH, HashNet, GreedyHash, IDHN, CSQ and DPN.
Multi-Headed Self-Attention via Vision Transformer for Zero-Shot Learning (ViT-ZSL)
VTHSC-MIR: Vision Transformer Hashing with Supervised Contrastive learning based medical image retrieval