{"id":20339274,"url":"https://github.com/encounter1997/arxiv-daily","last_synced_at":"2026-03-07T11:32:29.240Z","repository":{"id":158022770,"uuid":"349001396","full_name":"encounter1997/Arxiv-Daily","owner":"encounter1997","description":"My daily arxiv reading note","archived":false,"fork":false,"pushed_at":"2021-11-10T03:14:41.000Z","size":405,"stargazers_count":30,"open_issues_count":0,"forks_count":1,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-12-05T05:52:30.319Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/encounter1997.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-03-18T08:48:25.000Z","updated_at":"2024-09-23T11:17:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"fdc36dd6-78ac-4763-963f-326874c6992d","html_url":"https://github.com/encounter1997/Arxiv-Daily","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/encounter1997/Arxiv-Daily","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/encounter1997%2FArxiv-Daily","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/encounter1997%2FArxiv-Daily/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/encounter1997%2FArxiv-Daily/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/encounter1997%2FArxiv-Daily/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/encounter1997","download_url":"https://codeload.github.com/encounter1997/Arxiv-Daily/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/encounter1997%2FArxiv-Daily/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30212124,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-07T09:02:10.694Z","status":"ssl_error","status_checked_at":"2026-03-07T09:02:08.429Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-14T21:16:08.783Z","updated_at":"2026-03-07T11:32:29.176Z","avatar_url":"https://github.com/encounter1997.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Arxiv-Daily\n\nMy daily arxiv reading notes.  \n\n[2021 March](202103.md)\n\n[2021 April](202104.md)\n\n[2021 June](202106.md)\n\n[2021 July](202107.md)\n\n[2021 Aug](202108.md)\n\n[2021 Sep](202109.md)\n\n## CV (Daily)\n\n#### 20211108\n\n* :star: ​[EditGAN: High-Precision Semantic Image Editing](https://arxiv.org/pdf/2111.03186.pdf) (NVIDIA, MIT) NIPS\n* [Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers](https://arxiv.org/pdf/2111.03481.pdf) (jianlong fu) NIPS\n  * 用transformer做图像生成，避免生搬硬套的角度：（1）逐个token的生成有利于保证生成图像的局部特性（2）new perspective: token-based generator\n\n#### 20211110\n\n* [Data Augmentation Can Improve Robustness](https://arxiv.org/pdf/2111.05328.pdf) (NIPS21)\n\n  * 对抗训练会面临鲁棒性过拟合问题，本文提出一种数据增强方法来提升鲁棒性\n  * Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. \n  * We demonstrate that, contrary to previous findings, when combined with model weight averaging, data augmentation can significantly boost robust accuracy.\n\n* [Sliced Recursive Transformer](https://arxiv.org/pdf/2111.05297.pdf) (Eric Xing)\n\n  * ICLR submission (65553)\n  * We present a neat yet effective recursive operation on vision transformers that can improve parameter utilization without involving additional parameters. This is achieved by sharing weights across depth of transformer networks.\n\n* [MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps](https://arxiv.org/pdf/2111.05073.pdf)  (NIPS21)\n\n  * 提升对抗鲁棒性的最常用方法还是对抗训练，本文提出一种alternative，通过知识蒸馏用鲁棒teacher网络提升student鲁棒性\n\n  * First, we theoretically show the transferability of robustness from an adversarially trained teacher model to a student model with the help of mixup augmentation. \n  * MixACM transfers robustness from a robust teacher to a student by matching activated channel maps generated without expensive adversarial perturbations\n\n* [Self-Interpretable Model with Transformation Equivariant Interpretation]() (NIPS21)\n\n  * 解释性网络稳定性很差，容易受到数据扰动或变换的干扰。本文提出一种鲁棒的解释性方法，它在self-interpretable model中引入变换的不变性约束。\n  * Recent studies have found that interpretation methods can be sensitive and unreliable, where the interpretations can be disturbed by perturbations or transformations of input data. \n  * To address this issue, we propose to learn robust interpretations through transformation equivariant regularization in a self-interpretable model.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fencounter1997%2Farxiv-daily","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fencounter1997%2Farxiv-daily","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fencounter1997%2Farxiv-daily/lists"}