Cover image for Scientific Image Forgery Detection ā€” Kaggle Competition Part...
Scientific Image Forgery Detection ā€” Kaggle Competition Participated in the ongoing Kaggle competition on Copy-Move Forgery Detection in Scientific Images, aimed at identifying manipulated biomedical figures that can compromise research integrity. For this challenge, I developed a ResNet50 + U-Net hybrid segmentation model using PyTorch, designed to detect and segment forged regions at the pixel level. My approach combines Dice and Focal losses for balanced training, WeightedRandomSampling to oversample forged images, and Test-Time Augmentation (TTA) to improve prediction robustness. Achieved an initial score of 0.303 on the public leaderboard. Iā€™m continuing to experiment with architecture tuning, learning rate schedules, and other loss functions to further enhance performance and generalization.
0
31
Cover image for In this project, I developed a Sentiment Analysis Web App us...
In this project, I developed a Sentiment Analysis Web App using deep learning (CNN) and traditional models to classify text sentiment with high accuracy. The system includes a complete evaluation pipeline comparing CNN, LSTM, Logistic Regression, Random Forest, and Naive Bayes ā€” analyzing performance across multiple iterations and datasets. Key Highlights: Built a Streamlit-based web app for real-time sentiment classification Developed and evaluated multiple models for accuracy and F1-score Created detailed analysis reports and prototype schematics Project here ā†’ GitHub Repository (https://github.com/Imkaran04/Sentiment_Analysis_Web_App/tree/main) Reports: Sentiment Analysis Report (PDF), Product Prototype Diagram Tech Stack: Python, Streamlit, TensorFlow/Keras, Scikit-learn, Matplotlib
0
18