Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Paper
•
1412.1897
•
Published
HoT
university
AI & ML interests
nlp vision xai
Recent Activity
anhng8Â
authored
14
papers
3 days ago
Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
Paper
•
1602.03616
•
Published
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Paper
•
1605.09304
•
Published
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Paper
•
1703.05830
•
Published
3DTouch: Towards a Wearable 3D Input Device for 3D Applications
Paper
•
1706.00176
•
Published
VectorDefense: Vectorization as a Defense to Adversarial Examples
Paper
•
1804.08529
•
Published
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Paper
•
1811.11553
•
Published
Understanding Neural Networks via Feature Visualization: A survey
Paper
•
1904.08939
•
Published
•
1
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Paper
•
2403.05297
•
Published
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Paper
•
2502.09696
•
Published
•
44
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Paper
•
2503.02003
•
Published
•
48
Understanding Generative AI Capabilities in Everyday Image Editing Tasks
Paper
•
2505.16181
•
Published
•
23
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
Paper
•
2412.18675
•
Published
•
1
Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence
Paper
•
2501.05555
•
Published
•
1
ttn0011Â
updated
a
collection
3 months ago
ttn0011Â
updated
2
datasets
3 months ago
ttn0011Â
updated
a
collection
3 months ago
ttn0011Â
published
2
datasets
3 months ago