Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models

by   Dong Wang, et al.

Deep neural networks have shown significant promise in comprehending complex visual signals, delivering performance on par or even superior to that of human experts. However, these models often lack a mechanism for interpreting their predictions, and in some cases, particularly when the sample size is small, existing deep learning solutions tend to capture spurious correlations that compromise model generalizability on unseen inputs. In this work, we propose a contrastive causal representation learning strategy that leverages proactive interventions to identify causally-relevant image features, called Proactive Pseudo-Intervention (PPI). This approach is complemented with a causal salience map visualization module, i.e., Weight Back Propagation (WBP), that identifies important pixels in the raw input image, which greatly facilitates the interpretability of predictions. To validate its utility, our model is benchmarked extensively on both standard natural images and challenging medical image datasets. We show this new contrastive causal representation learning model consistently improves model performance relative to competing solutions, particularly for out-of-domain predictions or when dealing with data integration from heterogeneous sources. Further, our causal saliency maps are more succinct and meaningful relative to their non-causal counterparts.


page 2

page 6

page 7

page 8

page 16

page 18

page 19

page 20


Contrastive Unsupervised Learning of World Model with Invariant Causal Features

In this paper we present a world model, which learns causal features usi...

iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects

Causal representation learning is the task of identifying the underlying...

i-Mix: A Strategy for Regularizing Contrastive Representation Learning

Contrastive representation learning has shown to be an effective way of ...

Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation

This paper presents a simple yet effective two-stage framework for semi-...

A Survey on Causal Representation Learning and Future Work for Medical Image Analysis

Statistical machine learning algorithms have achieved state-of-the-art r...

Interventional Contrastive Learning with Meta Semantic Regularizer

Contrastive learning (CL)-based self-supervised learning models learn vi...

EiHi Net: Out-of-Distribution Generalization Paradigm

This paper develops a new EiHi net to solve the out-of-distribution (OoD...

Please sign up or login with your details

Forgot password? Click here to reset