{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:32Z","timestamp":1774420112964,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889443","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Attention Augmented Structure-centric Bias Mitigation with Feature Disentanglement"],"prefix":"10.1109","author":[{"given":"Xuege","family":"Hou","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"528","article-title":"Learning de-biased representations with biased representations","volume-title":"Proc. Int. Conf. Machine Learning","author":"Bahng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00922"},{"key":"ref3","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018"},{"key":"ref4","article-title":"RUBi: Reducing Unimodal Biases for Visual Question Answering","volume-title":"Advances in Neural Information Processing Systems","author":"Cadene"},{"key":"ref5","article-title":"Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet","author":"Brendel","year":"2019"},{"key":"ref6","first-page":"20673","article-title":"Learning from failure: De-biasing classifier from biased classifier","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Nam"},{"key":"ref7","first-page":"25123","article-title":"Learning debiased representation via disentangled feature augmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Lee"},{"key":"ref8","article-title":"Adversarial examples are not bugs, they are features","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ilyas"},{"key":"ref9","first-page":"6927","article-title":"Automatic shortcut removal for self-supervised representation learning","volume-title":"International Conference on Machine Learning","author":"Minderer"},{"key":"ref10","article-title":"Con-TNet: Why not use convolution and transformer at the same time?","author":"Yan","year":"2021"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N18-2074","article-title":"Self-attention with relative position representations","author":"Shaw","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01472"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00367"},{"key":"ref15","first-page":"15316","article-title":"Augmented shortcuts for vision transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Tang"},{"key":"ref16","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Citeseer"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref20","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Xiao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref22","article-title":"Adversarial Examples are not Bugs, they are Features","author":"Ilyas","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/538161a"},{"key":"ref24","article-title":"On the biases of pretrained language models","author":"Mohamed","year":"2019"},{"issue":"2","key":"ref25","first-page":"1505","article-title":"Causal Inference for Fair Representation Learning by Entropy Minimization","volume-title":"Proc. 2021 AAAI Conf. Artificial Intelligence (AAAI)","volume":"35","author":"Zaheer"},{"key":"ref26","first-page":"70","article-title":"Learning a Fair Representation","volume-title":"Proc. 34th Int. Conf. Machine Learning (ICML)","author":"Agarwal"},{"key":"ref27","article-title":"Bias mitigation through self-supervised learning with marginalized representations","author":"Lim","journal-title":"IEEE Trans"},{"key":"ref28","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations[C]","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref29","first-page":"30392","article-title":"Early convolutions help transformers see better[J]","volume-title":"Advances in neural information processing systems","volume":"34","author":"Xiao"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889443.pdf?arnumber=10889443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:27Z","timestamp":1774416387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889443","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}