Anh (Totti) Nguyen

XAI-papers.

vision-llms-are-blind. Python

gScoreCAM. Python

deepface-emd. Code for CVPR 2022 https://arxiv.org/abs/2112.04016 DeepFace-EMD Re-ranking Using Patch-wise Earth Movers Distance Improves Out-Of-Distribution Face Identification

visual-correspondence-XAI. Official code for NeurIPS 2022 paper https://arxiv.org/abs/2208.00780 Visual correspondence-based explanations improve AI robustness and human-AI team accuracy

sam. Code for the CVPR 2020 [ORAL] paper "SAM: The Sensitivity of Attribution Methods to Hyperparameters"

face-vit. Python

effectiveness-attribution-maps. Data for the NeurIPS 2021 paper [The effectiveness of feature attribution methods and its correlation with automatic evaluation scores] https://arxiv.org/abs/2105.14944

generative-attribution-methods. Code for paper [Explaining image classifiers by removing input features using generative models] [ACCV 2020] https://arxiv.org/abs/1910.04256

peeb. [NAACL 2024] Part-based, explainable and editable fine-grained image classifier that allows users to define a species in text

image-diff. Python

Deep-Learning-Papers-Reading-Roadmap. Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

deep-visualization-toolbox. Added support for Touchscreen (Ubuntu 14)

im. Code for [ Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models? ] AACL 2022 https://arxiv.org/abs/2110.11929

chm-corr-interactive. Python

caffe_lrcn. A clone from the recurrent branch of the LRCN caffe by Jeff Donahue http://jeffdonahue.com/lrcn/

TAB. Python

nearest-neighbor-XAI. Python

hot. Python

b-score. Python

pos. Interpretable LLM-based Table Question Answering

biggan-am. BigGAN-AM improves the sample diversity of BigGAN and synthesizes Places365 images.

shape-bias. Code for [The shape and simplicity biases of adversarially robust ImageNet-trained CNNs] https://arxiv.org/abs/2006.09373

DCGAN-tensorflow. A tensorflow implementation of Deep Convolutional Generative Adversarial Networks

cnn-vis. Use CNNs to generate images

screenfull.js. Simple wrapper for cross-browser usage of the JavaScript Fullscreen API

jquery-validation. jQuery Validation Plugin