mlsanityData to 7 Oct 2026

Analyzing the Performance of Multilayer Neural Networks for Object Recognition

arXiv 1407.1610 ↗First posted 7 Jul 2014cs.CV cs.NEcited by 29

Not on the map. Why?

Abstract (arXiv)

In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jul 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 10; 2023: 6; 2024: 3; 2025: 2; 2026: 1.

29 papers.

Sort:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  2. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  3. 2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
  4. 2022Finding Skill Neurons in Pre-trained Transformer-based Language Modelscited by 65
  5. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  6. 2022Pro-tuning: Unified Prompt Tuning for Vision Taskscited by 53
  7. 2021Scalable Diverse Model Selection for Accessible Transfer Learningcited by 40
  8. 2021Self-Tuning for Data-Efficient Deep Learningcited by 39
  9. 2022Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learningcited by 39
  10. 2021Zoo-Tuning: Adaptive Transfer from a Zoo of Modelscited by 35
  11. 2022Prompt-Matched Semantic Segmentationcited by 22
  12. 2022Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferabilitycited by 21
17 more
  1. 2021Hebbian Semi-Supervised Learning in a Sample Efficiency Settingcited by 19
  2. 2022Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transportcited by 19
  3. 2022Deep transfer learning for image classification: a surveycited by 13
  4. 2025General Intelligence Requires Reward-based Pretrainingcited by 12
  5. 2023A Holistic Assessment of the Reliability of Machine Learning Systemscited by 9
  6. 2021DAP: Detection-Aware Pre-training with Weak Supervisioncited by 7
  7. 2023Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Surveycited by 7
  8. 2022Hub-Pathway: Transfer Learning from A Hub of Pre-trained Modelscited by 5
  9. 2023Simple Transferability Estimation for Regression Taskscited by 5
  10. 2022Transfer Learning with Pre-trained Conditional Generative Modelscited by 4
  11. 2021Non-binary deep transfer learning for image classificationcited by 2
  12. 2024Semantically-correlated memories in a dense associative modelcited by 2
  13. 2024Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networkscited by 1
  14. 2026Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representationscited by 1
  15. 2023EscherNet 101cited by 0
  16. 2024GTA: Guided Transfer of Spatial Attention from Object-Centric Representationscited by 0
  17. 2025Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Modelcited by 0