Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks
cs.CV
Submitted: 2026-09-01
Updated: 2026-11-03
Code: https://github.com/XAI4SAR/SARHUB
Terminology
Sources
- Understanding the Double Descent Phenomenon in Deep Learning
- Scaling Laws for Neural Language Models
- Deep Learning Scaling is Predictable, Empirically
- Training Neural Networks at Any Scale
- An Empirical Study of Training Self-Supervised Vision Transformers
- A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning
- Overparameterization and generalization error: weighted trigonometric interpolation
- Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
- Additional Representations for Improving Synthetic Aperture Sonar Classification Using Convolutional Neural Networks
- Structural Prior Driven Regularized Deep Learning for Sonar Image Classification
- On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery
- A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
- Deep Residual Learning for Image Recognition
- Aggregated Residual Transformations for Deep Neural Networks
- A ConvNet for the 2020s
- HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
- Adam: A Method for Stochastic Optimization
- ImageNet Large Scale Visual Recognition Challenge
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
- Training data-efficient image transformers & distillation through attention
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs