paper-with-me

홈 › Papers

Counterfactual Image Networks

2018-01-01 · ICLR 2018 1 · Deniz Oktay, Carl Vondrick, Antonio Torralba

We capitalize on the natural compositional structure of images in order to learn object segmentation with weakly labeled images. The intuition behind our approach is that removing objects from images will yield natural images, however removing random patches will yield unnatural images. We leverage this signal to develop a generative model that decomposes an image into layers, and when all layers are combined, it reconstructs the input image. However, when a layer is removed, the model learns to produce a different image that still looks natural to an adversary, which is possible by removing objects. Experiments and visualizations suggest that this model automatically learns object segmentation on images labeled only by scene better than baselines.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualObjectSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

2023-09-23 · NeurIPS 2023 11

Counterfactual examples have proven to be valuable in the field of natural language processing (NLP) for both evaluating and improving the robustness of language models to spurious correlations in datasets. Despite their…

counterfactualData AugmentationDomain Generalization

Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals

2020-09-17 · Saloni Dash, Vineeth N Balasubramanian, Amit Sharma

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups…

BIG-bench Machine LearningcounterfactualFairnessvalid

Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models

2023-11-20 · Indu Ilanchezian, Valentyn Boreiko, Laura Kühlewein, Ziwei Huang 외

Counterfactual reasoning is often used in clinical settings to explain decisions or weigh alternatives. Therefore, for imaging based specialties such as ophthalmology, it would be beneficial to be able to create counterf…

counterfactualCounterfactual Reasoning

DeDUCE: Generating Counterfactual Explanations Efficiently

2021-11-29 · Benedikt Höltgen, Lisa Schut, Jan M. Brauner, Yarin Gal

When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. Howev…

counterfactual

Measuring axiomatic soundness of counterfactual image models

2023-03-02 · Miguel Monteiro, Fabio De Sousa Ribeiro, Nick Pawlowski, Daniel C. Castro 외

We present a general framework for evaluating image counterfactuals. The power and flexibility of deep generative models make them valuable tools for learning mechanisms in structural causal models. However, their flexib…

counterfactualCounterfactual Inference