mlsanityData to 14 Oct 2026

Multi-layer Representation Learning for Robust OOD Image Classification

arXiv 2207.13678 ↗First posted 27 Jul 2022cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past few years. In order to utilize such models in real-world scenarios and applications, they must be able to provide trustworthy predictions on unseen data. In this paper, we argue that extracting features from a CNN's intermediate layers can assist in the model's final prediction. Specifically, we adapt the Hypercolumns method to a ResNet-18 and find a significant increase in the model's accuracy, when evaluating on the NICO dataset.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 27 Jul 2022.

Builds on

16 of 22 references.

References · 16

  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  3. 2019Invariant Risk Minimizationcited by 1,854
  4. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  5. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  6. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  9. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
  10. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  11. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  12. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
4 more
  1. 2020A Survey of Deep Meta-Learningcited by 100
  2. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  3. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  4. 2020DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentationcited by 48

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1.

5 papers.

  1. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  2. 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
  3. 2023Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarkscited by 14
  4. 2023CNN Feature Map Augmentation for Single-Source Domain Generalizationcited by 4
  5. 2023Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalizationcited by 4