Recursive Counterfactual Deconfounding for Object Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualObjectObject RecognitionOpen Set LearningSimilar Papers 제목 키워드 기반
Synergizing Deconfounding and Temporal Generalization For Time-series Counterfactual Outcome Estimation
Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantly challenging because (i) the counterfac…
Debiased Counterfactual Generation via Flow Matching from Observations
Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks. Existing approaches model the counterfactual distribution as a standalone generativ…
Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization
Attribute bias in federated learning (FL) typically leads local models to optimize inconsistently due to the learning of non-causal associations, resulting degraded performance. Existing methods either use data augmentat…
AttributeBenchmarkingcounterfactualData Augmentation+3DeCaFlow: A Deconfounding Causal Generative Model
We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate causal inference on continuous variables …
Causal InferencecounterfactualmodelDiversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure
Beyond user-item modeling, item-to-item relationships are increasingly used to enhance recommendation. However, common methods largely rely on co-occurrence, making them prone to item popularity bias and user attributes,…