[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

by   Sunnie S. Y. Kim, et al.

Singh et al. (2020) point out the dangers of contextual bias in visual recognition datasets. They propose two methods, CAM-based and feature-split, that better recognize an object or attribute in the absence of its typical context while maintaining competitive within-context accuracy. To verify their performance, we attempted to reproduce all 12 tables in the original paper, including those in the appendix. We also conducted additional experiments to better understand the proposed methods, including increasing the regularization in CAM-based and removing the weighted loss in feature-split. As the original code was not made available, we implemented the entire pipeline from scratch in PyTorch 1.7.0. Our implementation is based on the paper and email exchanges with the authors. We found that both proposed methods in the original paper help mitigate contextual bias, although for some methods, we could not completely replicate the quantitative results in the paper even after completing an extensive hyperparameter search. For example, on COCO-Stuff, DeepFashion, and UnRel, our feature-split model achieved an increase in accuracy on out-of-context images over the standard baseline, whereas on AwA, we saw a drop in performance. For the proposed CAM-based method, we were able to reproduce the original paper's results to within 0.5% mAP. Our implementation can be found at https://github.com/princetonvisualai/ContextualBias.


page 4

page 8

page 17

page 18


Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Existing models often leverage co-occurrences between objects and their ...

Agile Effort Estimation: Have We Solved the Problem Yet? Insights From A Second Replication Study (GPT2SP Replication Report)

Fu and Tantithamthavorn have recently proposed GPT2SP, a Transformer-bas...

Model soups to increase inference without increasing compute time

In this paper, we compare Model Soups performances on three different mo...

Multi-Feature Integration for Perception-Dependent Examination-Bias Estimation

Eliminating examination bias accurately is pivotal to apply click-throug...

Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance

Gradient Boosting Decision Tree (GBDT) has achieved remarkable success i...

LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem

In computer vision, the performance of deep neural networks (DNNs) is hi...

Learning correspondences of cardiac motion from images using biomechanics-informed modeling

Learning spatial-temporal correspondences in cardiac motion from images ...

Please sign up or login with your details

Forgot password? Click here to reset