MobileMold provides 4941 smartphone microscopy images and shows deep learning models reach 99.5% accuracy on mold detection and food classification tasks.
Canonical reference
Exploiting visual artifacts to expose deepfakes and face manipulations
Canonical reference. 100% of citing Pith papers cite this work as background.
12
Pith papers citing it
2,736
external citations · external index
Background
100% of classified citations
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
CRDA augments regression datasets by generating counterfactual samples from invariant residuals, cutting MLP MSE by 22.9% and XGBoost MSE by 6.4% on average across benchmarks.
RBFN projection heads serve as competitive replacements for MLP heads in SSL and enable SNS, a label-free metric from RBF parameters that correlates strongly with logistic regression evaluation.
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
CutMix augmentation during training induces spatial locality in early layers of Vision Transformers trained from scratch, as measured by reduced Mean Attention Distance.
Small-scale programs exhibit notable compile-time and run-time configurability that grows over time and correlates with size, supporting the value of reducing variability for simpler software.
Video forgeries are detectable via binary classification on multimedia stream descriptors without pixel analysis.
It gives an explicit infinite ternary word with no parameterized squares of half-length at least 3 and an explicit infinite binary word with no order-preserving squares of half-length at least 3, plus finite extremal lengths.
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
Derivation of the incompressible XMHD dispersion relation yields ion cyclotron and whistler branches that saturate at the ion and electron gyrofrequencies, providing a smoother description than Hall MHD at high wave numbers.
This paper proposes a research agenda for software engineering of self-adaptive robotic systems along lifecycle stages and enabling technologies, identifying challenges and a roadmap to 2030.
The QBF Gallery 2023 report consolidates submitted solvers and formulas into a public benchmark set and compares solver performance on it while outlining future directions for the community.
citing papers explorer
-
MobileMold: A Smartphone-Based Microscopy Dataset for Food Mold Detection
MobileMold provides 4941 smartphone microscopy images and shows deep learning models reach 99.5% accuracy on mold detection and food classification tasks.
-
Counterfactual Residual Data Augmentation for Regression
CRDA augments regression datasets by generating counterfactual samples from invariant residuals, cutting MLP MSE by 22.9% and XGBoost MSE by 6.4% on average across benchmarks.
-
Radial Basis Function Networks as Projection Heads in Self-Supervised Learning
RBFN projection heads serve as competitive replacements for MLP heads in SSL and enable SNS, a label-free metric from RBF parameters that correlates strongly with logistic regression evaluation.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
Inducing Spatial Locality in Vision Transformers through the Training Protocol
CutMix augmentation during training induces spatial locality in early layers of Vision Transformers trained from scratch, as measured by reduced Mean Attention Distance.
-
Small Yet Configurable: Unveiling Null Variability in Software
Small-scale programs exhibit notable compile-time and run-time configurability that grows over time and correlates with size, supporting the value of reducing variability for simpler software.
-
We Need No Pixels: Video Manipulation Detection Using Stream Descriptors
Video forgeries are detectable via binary classification on multimedia stream descriptors without pixel analysis.
-
Relaxation of Square-Freeness
It gives an explicit infinite ternary word with no parameterized squares of half-length at least 3 and an explicit infinite binary word with no order-preserving squares of half-length at least 3, plus finite extremal lengths.
-
Out-of-Distribution Generalization in Time Series: A Survey
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
-
Incompressible Extended Magnetohydrodynamics Waves: Implications of Electron Inertia
Derivation of the incompressible XMHD dispersion relation yields ion cyclotron and whistler branches that saturate at the ion and electron gyrofrequencies, providing a smoother description than Hall MHD at high wave numbers.
-
Software Engineering for Self-Adaptive Robotics: A Research Agenda
This paper proposes a research agenda for software engineering of self-adaptive robotic systems along lifecycle stages and enabling technologies, identifying challenges and a roadmap to 2030.
-
The QBF Gallery 2023
The QBF Gallery 2023 report consolidates submitted solvers and formulas into a public benchmark set and compares solver performance on it while outlining future directions for the community.