Fetching the paper…
Reading the bibliography…
A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse.
Visualizing data using t-sne
Laurens van der Maaten and Geoffrey Hinton · 2008
Earlier work this paper cites.
Microsoft coco: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick · 2014
Earlier work this paper cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
Gender shades: Intersectional accuracy disparities in commercial gender classification
Joy Buolamwini and Timnit Gebru · 2018
Earlier work this paper cites.
Interpretable dimensionality reduction of single cell transcriptome data with deep generative models
Jiarui Ding, Anne Condon, and Sohrab P Shah · 2018
Earlier work this paper cites.
Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)
Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al · 2018
Earlier work this paper cites.
Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper R. R. Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Tom Duerig, and Vittorio Ferrari · 2018
Earlier work this paper cites.
Fairvis: Visual analytics for discovering intersectional bias in machine learning
Ángel Alexander Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, and Duen Horng Chau · 2019
Earlier work this paper cites.
Slice finder: Automated data slicing for model validation
Yeounoh Chung, Tim Kraska, Neoklis Polyzotis, Ki Hyun Tae, and Steven Euijong Whang · 2019
Earlier work this paper cites.
Summit: Scaling deep learning interpretability by visualizing activation and attribution summarizations
Fred Hohman, Haekyu Park, Caleb Robinson, and Duen Horng Polo Chau · 2019
Earlier work this paper cites.
Multiaccuracy: Black-box post-processing for fairness in classification
Michael P Kim, Amirata Ghorbani, and James Zou · 2019
Earlier work this paper cites.
Not using the car to see the sidewalk–quantifying and controlling the effects of context in classification and segmentation
Rakshith Shetty, Bernt Schiele, and Mario Fritz · 2019
Earlier work this paper cites.
Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition
Julia K Winkler, Christine Fink, Ferdinand Toberer, Alexander Enk, Teresa Deinlein, Rainer Hofmann-Wellenhof, Luc Thomas, Aimilios Lallas, Andreas Blum, Wilhelm Stolz, et al · 2019
Earlier work this paper cites.
Interactive clustering: A comprehensive review
Juhee Bae, Tove Helldin, Maria Riveiro, Sławomir Nowaczyk, Mohamed-Rafik Bouguelia, and Göran Falkman · 2020
Earlier work this paper cites.
What neural networks memorize and why: Discovering the long tail via influence estimation
Vitaly Feldman and Chiyuan Zhang · 2020
Earlier work this paper cites.
What shapes feature representations? exploring datasets, architectures, and training, 2020
Katherine L. Hermann and Andrew K. Lampinen · 2020
Cited alongside, same era.
Hidden stratification causes clinically meaningful failures in machine learning for medical imaging
Luke Oakden-Rayner, Jared Dunnmon, Gustavo Carneiro, and Christopher Ré · 2020
Cited alongside, same era.
Distributionally robust neural networks
Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, and Percy Liang · 2020
Cited alongside, same era.
Don’t judge an object by its context: Learning to overcome contextual bias
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, and Deepti Ghadiyaram · 2020
Cited alongside, same era.
Explanation by progressive exaggeration
Sumedha Singla, Brian Pollack, Junxiang Chen, and Kayhan Batmanghelich · 2020
Cited alongside, same era.
No subclass left behind: Fine-grained robustness in coarse-grained classification problems
Understanding failures of deep networks via robust feature extraction
Sahil Singla, Besmira Nushi, Shital Shah, Ece Kamar, and Eric Horvitz · 2021
Later among the works it cites.
Noise or signal: The role of image backgrounds in object recognition
Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, and Aleksander Madry · 2021
Later among the works it cites.
Post hoc explanations may be ineffective for detecting unknown spurious correlation
Julius Adebayo, Michael Muelly, Harold Abelson, and Been Kim · 2022
Closest in time.
How can explainability methods be used to support bug identification in computer vision models?
Agathe Balayn, Natasa Rikalo, Christoph Lofi, Jie Yang, and Alessandro Bozzon · 2022
Closest in time.
Domino: Discovering systematic errors with cross-modal embeddings
Sabri Eyuboglu, Maya Varma, Khaled Kamal Saab, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, and Christopher Re · 2022
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Nimit Sohoni, Jared Dunnmon, Geoffrey Angus, Albert Gu, and Christopher Ré · 2020
Cited alongside, same era.
On completeness-aware concept-based explanations in deep neural networks
Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li, Tomas Pfister, and Pradeep Ravikumar · 2020
Cited alongside, same era.
The spotlight: A general method for discovering systematic errors in deep learning models
Greg d’Eon, Jason d’Eon, James R Wright, and Kevin Leyton-Brown · 2021
Cited alongside, same era.
Diagvib-6: A diagnostic benchmark suite for vision models in the presence of shortcut and generalization opportunities, 2021
Elias Eulig, Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Kilian Rambach, William Beluch, Xiahan Shi, and Volker Fischer · 2021
Cited alongside, same era.
Explaining in style: Training a GAN to explain a classifier in stylespace
Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, and Inbar Mosseri · 2021
Cited alongside, same era.
3db: A framework for debugging computer vision models
Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, et al · 2021
Cited alongside, same era.
Discover the unknown biased attribute of an image classifier, 2021
Zhiheng Li and Chenliang Xu · 2021
Cited alongside, same era.
Irena Gao, Gabriel Ilharco, Scott Lundberg, and Marco Tulio Ribeiro · 2022
Closest in time.
Sanity simulations for saliency methods
Joon Sik Kim, Gregory Plumb, and Ameet Talwalkar · 2022
Closest in time.
Discover and mitigate unknown biases with debiasing alternate networks
Zhiheng Li, Anthony Hoogs, and Chenliang Xu · 2022
Closest in time.
Finding and fixing spurious patterns with explanations
Gregory Plumb, Marco Tulio Ribeiro, and Ameet Talwalkar · 2022
Closest in time.
Seal: Interactive tool for systematic error analysis and labeling
Nazneen Rajani, Weixin Liang, Lingjiao Chen, Meg Mitchell, and James Zou · 2022
Closest in time.
Adaptive testing and debugging of nlp models
Marco Tulio Ribeiro and Scott Lundberg · 2022
Closest in time.
Zeno: An interactive framework for behavioral evaluation of machine learning
Ángel Alexander Cabrera, Erica Fu, Donald Bertucci, Kenneth Holstein, Ameet Talwalkar, Jason I. Hong, and Adam Perer · 2023
Closest in time.
Kaleidoscope: Semantically-grounded, context-specific ml model evaluation
Harini Suresh, Divya Shanmugam, Annie Bryan, Tiffany Chen, Alexander D’Amour, John V. Guttag, and Arvind Satyanarayan · 2023
Closest in time.
Discovering bugs in vision models using off-the-shelf image generation and captioning, 2023
Olivia Wiles, Isabela Albuquerque, and Sven Gowal · 2023
Closest in time.