Explore @sutd-visual-computing-group Open Source projects

SUTD Visual Computing Group (@sutd-visual-computing-group)

sutd-visual-computing-group

Stars
173
Global Org. Rank 43,692 (Top 14 %)
Registered over 4 years ago
Most used languages

Python
100.0 %
Location 🇸🇬 Singapore
Country Total Rank 921
Country Ranking

Python
253

dag-gans

Data Augmentation optimized for GAN

Fourier-Discrepancies-CNN-Detection

[CVPR 2021: Oral] In this work, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models.

Re-thinking_MI

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

awesome-generative-modeling-under-data-constraints

A Comprehensive List of Works for Generative Modeling with Limited Data, Few Shots, and Zero Shot

transferable-forensic-features

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

LS-KD-compatibility

[ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an LS-trained teacher with a low-temperature transfer to render high performance students.

KML-Classification

[NeurIPS 2021] Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning | PyTorch Implementation

google-streetview-gis-stack

This tool helps to generate Google Street View coverage maps by leveraging on Geographic Information System and Google Static Street View API

label-smoothing-multi-label-classification

Label Smoothing Experiment for Multi-label classification using Pascal VOC 2012 dataset

tokyo_24-7_image_retrieval_annotations

Annotated subset of Tokyo 24/7 Google Street View Dataset for Visual Geo-localization research. It consists of 16,000 dataset images and 49 distinct query locations taken at day/ evening/ night for a total of 147 query images.

research-reproducibility-guide-book

This Guide book is written with the intention of helping researchers and engineers working in machine learning domains to publish reproducible research.

FairTL