mlsanityData to 14 Oct 2026

Recursive Counterfactual Deconfounding for Object Recognition

arXiv 2309.13924 ↗First posted 25 Sep 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade. Most existing methods in literature aim to learn discriminative features from labeled images for classification, however, they generally neglect confounders that infiltrate into the learned features, resulting in low performances for discriminating test images. To address this problem, we propose a Recursive Counterfactual Deconfounding model for object recognition in both closed-set and open-set scenarios based on counterfactual analysis, called RCD. The proposed model consists of a factual graph and a counterfactual graph, where the relationships among image features, model predictions, and confounders are built and updated recursively for learning more discriminative features. It performs in a recursive manner so that subtler counterfactual features could be learned and eliminated progressively, and both the discriminability and generalization of the proposed model could be improved accordingly. In addition, a negative correlation constraint is designed for alleviating the negative effects of the counterfactual features further at the model training stage. Extensive experimental results on both closed-set recognition task and open-set recognition task demonstrate that the proposed RCD model performs better than 11 state-of-the-art baselines significantly in most cases.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

26 of 46 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  4. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  5. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  6. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  7. 2018Reducing Network Agnostophobiacited by 165
  8. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  9. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  10. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  11. 2018Robust Classification with Convolutional Prototype Learningcited by 123
  12. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
14 more
  1. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  2. 2020Hybrid Models for Open Set Recognitioncited by 109
  3. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  4. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  5. 2021Human Trajectory Prediction via Counterfactual Analysiscited by 42
  6. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  7. 2013ParceLiNGAM: A causal ordering method robust against latent confounderscited by 29
  8. 2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
  9. 2022PMAL: Open Set Recognition via Robust Prototype Miningcited by 27
  10. 2022Difficulty-Aware Simulator for Open Set Recognitioncited by 24
  11. 2020Open-Set Recognition with Gaussian Mixture Variational Autoencoderscited by 15
  12. 2022Towards Accurate Open-Set Recognition via Background-Class Regularizationcited by 10
  13. 2022OOD Augmentation May Be at Odds with Open-Set Recognitioncited by 6
  14. 2018A Kernel Embedding-based Approach for Nonstationary Causal Model Inferencecited by 1

Built on by

Not cited yet.