Anh Nguyen
- Papers
- 25
Cite
Notes
Only stored in your browser.
Authored papers
25MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
arXiv 2026
Adaptive Parametric Activation
arXiv 2024
FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
arXiv 2024
Fractal Calibration for long-tailed object detection
CVPR 2025 1
Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model
arXiv 2024
Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy
arXiv 2024
Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification
arXiv 2023
Music-Driven Group Choreography
CVPR 2023 1
I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses
arXiv 2023
Long-tailed Instance Segmentation using Gumbel Optimized Loss
arXiv 2022
Inverse Image Frequency for Long-tailed Image Recognition
arXiv 2022
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
arXiv 2022
Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology
ICCV 2023 1
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
arXiv 2022
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
CVPR 2022 1
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
NeurIPS 2021 12
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
arXiv 2021
Inverting Adversarially Robust Networks for Image Synthesis
arXiv 2021
Polychrony as Chinampas
arXiv 2021
SAM: The Sensitivity of Attribution Methods to Hyperparameters
sam-the-sensitivity-of-attribution-methods-to-1
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
arXiv 2019
Explaining image classifiers by removing input features using generative models
arXiv 2019
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
strike-with-a-pose-neural-networks-are-easily-1
VectorDefense: Vectorization as a Defense to Adversarial Examples
arXiv 2018
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
deep-neural-networks-are-easily-fooled-high-1
Affiliations
Frequent co-authors
10from 25 papers