mlsanityData to 7 Oct 2026

Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications

arXiv 1804.09028 ↗First posted 24 Apr 2018cs.LG cs.CL stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing applications into deep learning architectures. Using this approach, we estimate each application's functionality with an estimator, which is implemented as a deep neural network (DNN). The estimator is then embedded into a base network that we direct into complying with the application's interface during an end-to-end optimization process. At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application. Using this 'Estimate and Replace' method, we were able to train a DNN end-to-end with less data and outperformed a matching DNN that did not interact with the external application.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 7; 2025: 5; 2026: 1.

21 papers.

Sort:

By area:

  1. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  2. 2022Towards out of distribution generalization for problems in mechanicscited by 11
  3. 2022Facial Expression Recognition with Swin Transformercited by 9
  4. 2021Noise Optimization for Artificial Neural Networkscited by 7
  5. 2024The Dawn of KAN in Image-to-Image (I2I) Translation: Integrating Kolmogorov-Arnold Networks with GANs for Unpaired I2I Translationcited by 7
  6. 2023Multi Modal Facial Expression Recognition with Transformer-Based Fusion Networks and Dynamic Samplingcited by 2
  7. 2024Graph Neural Aggregation-diffusion with Metastabilitycited by 2
  8. 2024A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AIcited by 2
  9. 2025An h-space Based Adversarial Attack for Protection Against Few-shot Personalizationcited by 2
  10. 2023Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgettingcited by 1
  11. 2024Physics Sensor Based Deep Learning Fall Detection Systemcited by 1
  12. 2024Out-of-distribution detection based on subspace projection of high-dimensional features output by the last convolutional layercited by 1
9 more
  1. 2025Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generationcited by 1
  2. 2022Animating Still Imagescited by 0
  3. 2023Improved Breast Cancer Diagnosis through Transfer Learning on Hematoxylin and Eosin Stained Histology Imagescited by 0
  4. 2024DUNE: A Machine Learning Deep UNet++ based Ensemble Approach to Monthly, Seasonal and Annual Climate Forecastingcited by 0
  5. 2024REL: Working out is all you needcited by 0
  6. 2025ViRAC: A Vision-Reasoning Agent Head Movement Control Framework in Arbitrary Virtual Environmentscited by 0
  7. 2025Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Modelscited by 0
  8. 2025Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Reportcited by 0
  9. 2026Student Classroom Behavior Recognition Based on Improved YOLOv8scited by 0