arXiv Machine Learning
Jul 17
Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption
SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption proposes a new method for handling sample-heterogeneous corruption in multimodal training. The authors prove that batch-level, sample-agnostic linear estimators with a shared modulation parameter inevitably incur bias, and that a sample-level all-or-nothing gating strategy is the only unbiased approach within a natural estimator class. SAGG implements a binary retain-or-discard decision per sample using an online feature-norm quality test and a truncation mechanism for variance control, and demonstrates convergence to clean-loss stationary points while achieving superior performance over ten existing methods on Kinetics-Sounds and UCF-101 under various corruption scenarios.
Related stories
arXiv Computer Vision
5d ago
Sparsity-Adaptive Sharpness-Aware Minimization
The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.
arXiv AI
Aug 25
Mitigating Sample-Level Imbalance via Probabilistic Separation for Adaptive Multimodal Fusion
The paper introduces a framework to tackle modality imbalance in multimodal learning by focusing on sample-level variations. It defines a Modality Gap metric to measure prediction discrepancies, models the resulting bimodal distribution with a Gaussian Mixture Model, and uses Bayesian probabilities for soft separation of balanced and imbalanced samples. A two‑stage training process—Warm‑up and Adaptive Training—reallocates loss weights based on the GMM, strengthening alignment for imbalanced samples while favoring fusion for balanced ones, and shows superior performance over existing baselines.
arXiv AI
4d ago
Dual Randomized Smoothing: Beyond Global Noise Variance
arXiv:2512.01782v4 Announce Type: replace-cross Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With R...
arXiv AI
Jun 16
ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
arXiv Computer Vision
5d ago
Rethinking Gradient Modulation in Multimodal Regression
arXiv:2605.26513v2 Announce Type: replace Abstract: Even balanced multimodal learning methods do not consistently translate additional modalities into better regression performance. To understand thi...
arXiv Computer Vision
Sep 3
Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption
The paper introduces UnInfo, a test‑time adaptation method for vision‑language models like CLIP that addresses image corruption—a realistic distribution shift caused by sensor conditions. UnInfo leverages uniformity‑aware confidence maximization, information‑aware loss balancing, and knowledge distillation from an EMA teacher to preserve embedding uniformity and improve zero‑shot classification accuracy. Experiments show that UnInfo outperforms existing TTA methods on corrupted image datasets.
arXiv Machine Learning
Jun 24
Robust and Fast Training via Per-Sample Clipping
arXiv:2605. 02701v2 Announce Type: replace-cross Abstract: We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically.
arXiv AI
Jul 8
K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)
arXiv:2607. 05903v1 Announce Type: cross Abstract: We present K-ABENA (K-Adaptive Backpropagation with Error-based N-exclusion Algorithm), a selective gradient computation framework that reduces per-iteration training cost by excluding a fraction of low-loss ("minor") observations from the backward pass.
arXiv Machine Learning
Jun 9
Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation
arXiv:2606. 07660v1 Announce Type: cross Abstract: Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.
arXiv Machine Learning
Sep 1
Data Diversity, Not Frequency Invariance: A Controlled and Self-Audited Study of Compression-Robust Deepfake Detection
The study challenges the prevailing belief that frequency-based features and compression-invariant learning are essential for robust deepfake detection. Using a controlled, pre‑registered protocol, a simple EfficientNet‑B0 trained on diverse multi‑quality data outperformed the more complex CAFRL model across all compression levels, with a 3.66 AUC point advantage at CRF 40. After identifying and correcting four experimental defects, the authors found that frequency features added no marginal benefit, while data diversity—particularly real constant‑rate‑factor variants—proved to be the key factor for robustness against H.264 re‑encoding.
arXiv Machine Learning
Aug 4
GradientStabilizer:Fix the Norm, Not the Gradient
arXiv:2502. 17055v5 Announce Type: replace Abstract: Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence.