Fetching the paper…
Reading the bibliography…
Many past works aim to improve visual reasoning in models by supervising feature importance (estimated by model explanation techniques) with human annotations such as highlights of important image regions.
Saliency learning: Teaching the model where to pay attention
Reza Ghaeini, Xiaoli Z Fern, Hamed Shahbazi, and Prasad Tadepalli · 1902
Earlier work this paper cites.
Gradmask: Reduce overfitting by regularizing saliency
Becks Simpson, Francis Dutil, Yoshua Bengio, and Joseph Paul Cohen · 1904
Earlier work this paper cites.
Gabriel Erion, Joseph D Janizek, Pascal Sturmfels, Scott M Lundberg, and Su-In Lee · 1906
Earlier work this paper cites.
Attention is not not explanation
Sarah Wiegreffe and Yuval Pinter · 1908
Earlier work this paper cites.
Fine-grained sentiment analysis with faithful attention
Ruiqi Zhong, Steven Shao, and Kathleen McKeown · 1908
Earlier work this paper cites.
Eraser: A benchmark to evaluate rationalized nlp models
Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, and Byron C. Wallace · 1911
Earlier work this paper cites.
An Introduction to the Bootstrap
Bradley Efron and Robert J Tibshirani · 1994
Earlier work this paper cites.
Bleu: a method for automatic evaluation of machine translation
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu · 2002
Earlier work this paper cites.
The effect of natural distribution shift on question answering models
John Miller, Karl Krauth, Benjamin Recht, and Ludwig Schmidt · 2004
Earlier work this paper cites.
Learning what makes a difference from counterfactual examples and gradient supervision
Damien Teney, Ehsan Abbasnedjad, and Anton van den Hengel · 2004
Earlier work this paper cites.
Dataset shift in machine learning
Joaquin Quiñonero-Candela, Masashi Sugiyama, Anton Schwaighofer, and Neil D Lawrence · 2009
Earlier work this paper cites.
Formalizing trust in artificial intelligence: Prerequisites, causes and goals of human trust in ai
Alon Jacovi, Ana Marasović, Tim Miller, and Yoav Goldberg · 2010
Earlier work this paper cites.
Why do classifier accuracies show linear trends under distribution shift?
Horia Mania and Suvrit Sra · 2012
Earlier work this paper cites.
Object-centric diagnosis of visual reasoning
Jianwei Yang, Jiayuan Mao, Jiajun Wu, Devi Parikh, David D Cox, Joshua B Tenenbaum, and Chuang Gan · 2012
Earlier work this paper cites.
Deep inside convolutional networks: Visualising image classification models and saliency maps
Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Diederik P Kingma and Jimmy Ba · 2014
Earlier work this paper cites.
Vqa: Visual question answering
Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh · 2015
Earlier work this paper cites.
Principles of explanatory debugging to personalize interactive machine learning
Todd Kulesza, Margaret Burnett, Weng-Keen Wong, and Simone Stumpf · 2015
Earlier work this paper cites.
Faster r-cnn: Towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun · 2015
Earlier work this paper cites.
Human attention in visual question answering: Do humans and deep networks look at the same regions?
Abhishek Das, Harsh Agrawal, Larry Zitnick, Devi Parikh, and Dhruv Batra · 2017
Earlier work this paper cites.
Clevr: A diagnostic dataset for compositional language and elementary visual reasoning
Justin Johnson, Bharath Hariharan, Laurens Van Der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick · 2017
Earlier work this paper cites.
Visual genome: Connecting language and vision using crowdsourced dense image annotations
Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A Shamma, et al · 2017
Earlier work this paper cites.
A Unified Approach to Interpreting Model Predictions
Scott M Lundberg and Su-In Lee · 2017
Cited alongside, same era.
Automatic differentiation in pytorch
Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer · 2017
Cited alongside, same era.
Right for the right reasons: Training differentiable models by constraining their explanations
Andrew Slavin Ross, Michael C. Hughes, and Finale Doshi-Velez · 2017
Cited alongside, same era.
Axiomatic attribution for deep networks
Mukund Sundararajan, Ankur Taly, and Qiqi Yan · 2017
Cited alongside, same era.
Don’t just assume; look and answer: Overcoming priors for visual question answering
Aishwarya Agrawal, Dhruv Batra, Devi Parikh, and Aniruddha Kembhavi · 2018
Cited alongside, same era.
ALICE: active learning with contrastive natural language explanations
Weixin Liang, James Zou, and Zhou Yu · 2020
Later among the works it cites.
A negative case analysis of visual grounding methods for VQA
Robik Shrestha, Kushal Kafle, and Christopher Kanan · 2020
Later among the works it cites.
Visualizing the impact of feature attribution baselines
Pascal Sturmfels, Scott Lundberg, and Su-In Lee · 2020
Later among the works it cites.
Measuring robustness to natural distribution shifts in image classification
Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, and Ludwig Schmidt · 2020
Later among the works it cites.
On the value of out-of-distribution testing: An example of goodhart’s law
Damien Teney, Ehsan Abbasnejad, Kushal Kafle, Robik Shrestha, Christopher Kanan, and Anton Van Den Hengel · 2020
Later among the works it cites.
Clevr-xai: A benchmark dataset for the ground truth evaluation of neural network explanations
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Bottom-up and top-down attention for image captioning and visual question answering
Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang · 2018
Cited alongside, same era.
Explanation in artificial intelligence: Insights from the social sciences
Tim Miller · 2018
Cited alongside, same era.
Evaluating recurrent neural network explanations
Leila Arras, Ahmed Osman, Klaus-Robert Müller, and Wojciech Samek · 2019
Cited alongside, same era.
Rubi: Reducing unimodal biases for visual question answering
Remi Cadene, Corentin Dancette, Matthieu Cord, Devi Parikh, et al · 2019
Cited alongside, same era.
Don’t take the easy way out: ensemble based methods for avoiding known dataset biases
Christopher Clark, Mark Yatskar, and Luke Zettlemoyer · 2019
Cited alongside, same era.
Bert: Pre-training of deep bidirectional transformers for language understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova · 2019
Cited alongside, same era.
Gqa: A new dataset for real-world visual reasoning and compositional question answering
Drew A Hudson and Christopher D Manning · 2019
Cited alongside, same era.
Leila Arras, Ahmed Osman, and Wojciech Samek · 2021
Later among the works it cites.
Towards robust classification model by counterfactual and invariant data generation
Chun-Hao Chang, George Alexandru Adam, and Anna Goldenberg · 2021
Later among the works it cites.
Enjoy the salience: Towards better transformer-based faithful explanations with word salience
George Chrysostomou and Nikolaos Aletras · 2021
Later among the works it cites.
Peter Hase, Harry Xie, and Mohit Bansal · 2021
Later among the works it cites.
Improving deep learning interpretability by saliency guided training
Aya Abdelsalam Ismail, Hector Corrada Bravo, and Soheil Feizi · 2021
Later among the works it cites.
To what extent do human explanations of model behavior align with actual model behavior?
Grusha Prasad, Yixin Nie, Mohit Bansal, Robin Jia, Douwe Kiela, and Adina Williams · 2021
Later among the works it cites.
A framework for understanding sources of harm throughout the machine learning life cycle
Harini Suresh and John Guttag · 2021
Later among the works it cites.
Ethical and social risks of harm from language models
Laura Weidinger, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, et al · 2021
Later among the works it cites.
A typology to explore and guide explanatory interactive machine learning
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski, and Kristian Kersting · 2022
Closest in time.
Aligning eyes between humans and deep neural network through interactive attention alignment
Yuyang Gao, Tong Sun, Liang Zhao, and Sungsoo Hong · 2022
Closest in time.
Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering
Vipul Gupta, Zhuowan Li, Adam Kortylewski, Chenyu Zhang, Yingwei Li, and Alan Yuille · 2022
Closest in time.
Er-test: Evaluating explanation regularization methods for nlp models
Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, and Xiang Ren · 2022
Closest in time.
Answer questions with right image regions: A visual attention regularization approach
Yibing Liu, Yangyang Guo, Jianhua Yin, Xuemeng Song, Weifeng Liu, Liqiang Nie, and Min Zhang · 2022
Closest in time.
Core risk minimization using salient imagenet
Sahil Singla, Mazda Moayeri, and Soheil Feizi · 2022
Closest in time.
Supervising model attention with human explanations for robust natural language inference
Joe Stacey, Yonatan Belinkov, and Marek Rei · 2022
Closest in time.
Id and ood performance are sometimes inversely correlated on real-world datasets
Damien Teney, Yong Lin, Seong Joon Oh, and Ehsan Abbasnejad · 2022
Closest in time.