Projects sharing features with STEAL

An example of CoreML using a pre-trained VGG16 model

Pulse is a generative model image upscaler and latent space image processor. It functions as a self-supervised photo upsampling tool that increases image resolution by exploring the latent space of pre-trained generative models to synthesize high-quality details. The system includes a face image alignment tool designed to standardize the scale and orientation of raw facial photos. This preprocessing utility prepares images for higher resolution processing by aligning and downscaling faces to a standard orientation. The project covers AI image super-resolution and generative photo upscaling,

Ranking-based-Instance-Selection

This is a PyTorch object detection framework that implements the Single Shot MultiBox Detector for identifying and localizing multiple objects within images and video. The project provides a neural network architecture designed for single-shot object detection, which predicts bounding boxes and class labels in one pass. The implementation includes a real-time object detector capable of processing live video streams to track and label objects across sequential frames. It also features a complete computer vision training pipeline for preparing image datasets and training model weights. The fra

Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21

Github repo for webly labeled learning of sound events

WACV'21: Do We Really Need Gold Samples for Sample Weighting Under Label Noise?

Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020

TCS humAIn This is a Flutter application that is used to locate the license plate out of a picture given to the application. Cue the Drum Rolls for what I am about to disclose. With the help of Sayak Paul the tensorflow model that was 255mb was cut short to a 2mb file. TFLite did the trick for…

Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)

Generate image analogies using neural matching and blending.

Auxiliary Image Regularization for Deep CNNs with Noisy labels at ICLR 2016

Official PyTorch implementation of "From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model" (ICML 2022) by HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon.

A PyTorch implementation of DenseNet.

This repository contains the pytroch code to reproduce the results the paper "Wasserstein Adversarial Regularization for Learning with Label Noise"

Classification with PyTorch.

Convolutional Recurrent Neural Network

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

NeurIPS'18: Masking: A New Perspective of Noisy Supervision

ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

Pixel-wise segmentation on the VOC2012dataset dataset using pytorchpytorch.

A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018