Domain Decorrelation with Potential Energy Ranking
Not on the map. Why?
Abstract (arXiv)
Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under experimental settings. Generally, these classic deep learning methods are built on the i.i.d. assumption, supposing the training and test data are drawn from a similar distribution independently and identically. However, the aforementioned i.i.d. assumption is in general unavailable in the real-world scenario, and as a result, leads to sharp performance decay of deep learning algorithms. Behind this, domain shift is one of the primary factors to be blamed. In order to tackle this problem, we propose using Potential Energy Ranking (PoER) to decouple the object feature and the domain feature (i.e., appearance feature) in given images, promoting the learning of label-discriminative features while filtering out the irrelevant correlations between the objects and the background. PoER helps the neural networks to capture label-related features which contain the domain information first in shallow layers and then distills the label-discriminative representations out progressively, enforcing the neural networks to be aware of the characteristic of objects and background which is vital to the generation of domain-invariant features. PoER reports superior performance on domain generalization benchmarks, improving the average top-1 accuracy by at least 1.20% compared to the existing methods. Moreover, we use PoER in the ECCV 2022 NICO Challengefootnotehttps://nicochallenge.com, achieving top place with only a vanilla ResNet-18. The code has been made available at https://github.com/ForeverPs/PoER.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 67 references that are in the map. First posted on arXiv 25 Jul 2022.
Builds on
51 of 67 references.
References · 51
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2022Generative Adversarial Networkscited by 5,627
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2015SSD: Single Shot MultiBox Detectorcited by 3,130
- 2017Improved Training of Wasserstein GANscited by 2,235
38 more
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
- 2014Conditional Generative Adversarial Netscited by 2,162
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
- 2014NICE: Non-linear Independent Components Estimationcited by 1,058
- 2017Deeper, Broader and Artier Domain Generalizationcited by 986
- 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
- 2013Domain Generalization via Invariant Feature Representationcited by 623
- 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
- 2021Domain Generalization with MixStylecited by 566
- 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
- 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
- 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
- 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
- 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
- 2020Learning to Learn Single Domain Generalizationcited by 296
- 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
- 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
- 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
- 2019Episodic Training for Domain Generalizationcited by 245
- 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
- 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
- 2020Domain Adaptive Ensemble Learningcited by 156
- 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
- 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
- 2018Robust Classification with Convolutional Prototype Learningcited by 123
- 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
- 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
- 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 97
- 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
- 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
- 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
- 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
- 2018Domain Generalization with Domain-Specific Aggregation Modulescited by 61
- 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2022: 2.
2 papers.