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

• URL: http://arxiv.org/abs/2104.13582v1
• Date: Wed, 28 Apr 2021 06:21:28 GMT
• Title: [Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
• Authors: Sunnie S. Y. Kim, Sharon Zhang, Nicole Meister, Olga Russakovsky
• Abstract summary: We implement the entire pipeline from scratch in PyTorch 1.7.0. We find that both proposed methods in the original paper help mitigate contextual bias.
• Score: 15.701707809084715
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• GHOST: Gaussian Hypothesis Open-Set Technique [10.426399605773083]
  Evaluations of large-scale recognition methods typically focus on overall performance. addressing fairness in Open-Set Recognition (OSR), we demonstrate that per-class performance can vary dramatically. We apply Z-score normalization to logits to mitigate the impact of feature magnitudes that deviate from the model's expectations.
  arXiv  Detail & Related papers  (2025-02-05T16:56:14Z)
• Explicit Relational Reasoning Network for Scene Text Detection [20.310201743941196]
  We introduce an explicit reasoning network (ERRNet) to elegantly model the component relationships without post-processing. ERRNet consistently achieves state-of-the-art accuracy while holding highly competitive inference speed.
  arXiv  Detail & Related papers  (2024-12-19T09:51:45Z)
• Fact Checking Beyond Training Set [64.88575826304024]
  We show that the retriever-reader suffers from performance deterioration when it is trained on labeled data from one domain and used in another domain. We propose an adversarial algorithm to make the retriever component robust against distribution shift. We then construct eight fact checking scenarios from these datasets, and compare our model to a set of strong baseline models.
  arXiv  Detail & Related papers  (2024-03-27T15:15:14Z)
• Theoretically Achieving Continuous Representation of Oriented Bounding Boxes [64.15627958879053]
  This paper endeavors to completely solve the issue of discontinuity in Oriented Bounding Box representation. We propose a novel representation method called Continuous OBB (COBB) which can be readily integrated into existing detectors. For fairness and transparency of experiments, we have developed a modularized benchmark based on the open-source deep learning framework Jittor's detection toolbox JDet for OOD evaluation.
  arXiv  Detail & Related papers  (2024-02-29T09:27:40Z)
• RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection [66.27699658243391]
  textttRankFeat is a simple yet effective emphpost hoc approach for OOD detection. textttRankWeight is also emphpost hoc and only requires computing the rank-1 matrix once. textttRankFeat achieves emphstate-of-the-art performance and reduces the average false positive rate (FPR95) by 17.90%.
  arXiv  Detail & Related papers  (2023-11-23T12:17:45Z)
• Detrimental Contexts in Open-Domain Question Answering [9.059854023578508]
  We analyze how passages can have a detrimental effect on retrieve-then-read architectures used in question answering. Our findings demonstrate that model accuracy can be improved by 10% on two popular QA datasets by filtering out detrimental passages.
  arXiv  Detail & Related papers  (2023-10-27T11:45:16Z)
• On Context Utilization in Summarization with Large Language Models [83.84459732796302]
  Large language models (LLMs) excel in abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, exceeding 100k tokens. We conduct the first comprehensive study on context utilization and position bias in summarization.
  arXiv  Detail & Related papers  (2023-10-16T16:45:12Z)
• Revisiting text decomposition methods for NLI-based factuality scoring of summaries [9.044665059626958]
  We show that fine-grained decomposition is not always a winning strategy for factuality scoring. We also show that small changes to previously proposed entailment-based scoring methods can result in better performance.
  arXiv  Detail & Related papers  (2022-11-30T09:54:37Z)
• Okapi: Generalising Better by Making Statistical Matches Match [7.392460712829188]
  Okapi is a simple, efficient, and general method for robust semi-supervised learning based on online statistical matching. Our method uses a nearest-neighbours-based matching procedure to generate cross-domain views for a consistency loss. We show that it is in fact possible to leverage additional unlabelled data to improve upon empirical risk minimisation.
  arXiv  Detail & Related papers  (2022-11-07T12:41:17Z)
• Content Popularity Prediction Based on Quantized Federated Bayesian Learning in Fog Radio Access Networks [76.16527095195893]
  We investigate the content popularity prediction problem in cache-enabled fog radio access networks (F-RANs) In order to predict the content popularity with high accuracy and low complexity, we propose a Gaussian process based regressor to model the content request pattern. We utilize Bayesian learning to train the model parameters, which is robust to overfitting.
  arXiv  Detail & Related papers  (2022-06-23T03:05:12Z)
• RepPoints V2: Verification Meets Regression for Object Detection [65.120827759348]
  We introduce verification tasks into the localization prediction of RepPoints. RepPoints v2 provides consistent improvements of about 2.0 mAP over the original RepPoints. We show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation.
  arXiv  Detail & Related papers  (2020-07-16T17:57:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.