mlsanityData to 7 Oct 2026

External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery

arXiv 2107.10504 ↗First posted 22 Jul 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a memory-based framework for real-time, data-efficient target analysis in forward-looking-sonar (FLS) imagery. Our framework relies on first removing non-discriminative details from the imagery using a small-scale DenseNet-inspired network. Doing so simplifies ensuing analyses and permits generalizing from few labeled examples. We then cascade the filtered imagery into a novel NeuralRAM-based convolutional matching network, NRMN, for low-shot target recognition. We employ a small-scale FlowNet, LFN to align and register FLS imagery across local temporal scales. LFN enables target label consensus voting across images and generally improves target detection and recognition rates. We evaluate our framework using real-world FLS imagery with multiple broad target classes that have high intra-class variability and rich sub-class structure. We show that few-shot learning, with anywhere from ten to thirty class-specific exemplars, performs similarly to supervised deep networks trained on hundreds of samples per class. Effective zero-shot learning is also possible. High performance is realized from the inductive-transfer properties of NRMNs when distractor elements are removed.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 69 of its 152 references that are in the map. First posted on arXiv 22 Jul 2021.

Builds on

69 of 152 references.

References · 69

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  11. 2015Fast R-CNNcited by 2,930
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
38 more
  1. 2016Matching Networks for One Shot Learningcited by 2,246
  2. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  3. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  7. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  8. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  12. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  13. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  14. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  15. 2014Memory Networkscited by 354
  16. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  17. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  18. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  19. 2017Meta Networkscited by 268
  20. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  21. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  22. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  23. 2017A General and Adaptive Robust Loss Functioncited by 236
  24. 2018Low-Shot Learning from Imaginary Datacited by 181
  25. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  26. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  27. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  28. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  29. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  30. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  31. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  32. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  33. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  34. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  35. 2016Learning feed-forward one-shot learnerscited by 93
  36. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  37. 2015Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networkscited by 80
  38. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74

50 most cited of 69 All 69 (JSON)

Built on by

Not cited yet.