Bryan A. Plummer

Bryan A. Plummer

Auto-generated profile, based on publicly available information

Bryan A. Plummer

Boston University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2022
Verified
Book Chapter
Closed access
PDF file
ABAndrea Burns
Andrea Burns
DADeniz Arsan
Deniz Arsan
SASanjna Agrawal
Sanjna Agrawal
RKRanjitha Kumar
Ranjitha Kumar
Kate SaenkoKate Saenko
Kate Saenko
BPBryan A. Plummer
Bryan A. Plummer

1 June 2023
Verified
Conference Paper
Open access
MQMaan Qraitem
Maan Qraitem
Kate SaenkoKate Saenko
Kate Saenko
BPBryan A. Plummer
Bryan A. Plummer
Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (e.g. Female) within class labels $Y$ (e.g. Programmers). This dataset bias can lead to models that learn spurious correlations between class labels and bias groups such as age, gender, or race. Most recent methods that address this problem require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Alternatively, data sampling baselines from the class imbalance literature (e.g. Undersampling, Upweighting), which can often be implemented in a single line of code and often have no hyperparameters, offer a cheaper and more efficient solution. However, these methods suffer from significant shortcomings. For example, Undersampling drops a significant part of the input distribution per epoch while Oversampling repeats samples, causing overfitting. To address these shortcomings, we introduce a new class-conditioned sampling method: Bias Mimicking. The method is based on the observation that if a class $c$ bias distribution, i.e. $P_{D}(B\vert Y=c)$ is mimicked across every $c^{\prime}\neq c$ , then $Y$ and $B$ are statistically independent. Using this notion, BM, through a novel training procedure, ensures that the model is exposed to the entire distribution per epoch without repeating samples. Consequently, Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks while maintaining and sometimes improving performance over nonsampling methods. Code: https://github.com/mqraitem/Bias-Mimicking

6 October 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
BPBryan A. Plummer
Bryan A. Plummer
KSKevin J. Shih
Kevin J. Shih
YLYichen Li
Yichen Li
KXKe Xu
Ke Xu
SLSvetlana Lazebnik
Svetlana Lazebnik
Kate SaenkoKate Saenko
Kate Saenko
Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initializing the classification layers of our network using canonical correlation analysis (CCA), we encourage a solution that is more discerning when reasoning between similar phrases, resulting in over double the performance compared to a naive adaptation on three popular phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, with test-time phrase vocabulary sizes of 5K, 32K, and 159K, respectively.


29 October 2020
Verified
Book Chapter
Closed access
PDF file
ABAndrea Burns
Andrea Burns
DKDonghyun Kim
Donghyun Kim
DWDerry Wijaya
Derry Wijaya
Kate SaenkoKate Saenko
Kate Saenko
BPBryan A. Plummer
Bryan A. Plummer

27 November 2020
Verified
Book Chapter
Closed access
PDF file
BPBryan A. Plummer
Bryan A. Plummer
MVMariya I. Vasileva
Mariya I. Vasileva
VPVitali Petsiuk
Vitali Petsiuk
KSKate Saenko
Kate Saenko
DFDavid Forsyth
David Forsyth