转载：计算机视觉Paper with code-2023.10.31

原文链接：计算机视觉Paper with code-2023.10.31

留存备用。

1.【基础网络架构】（NeurIPS2023）Fast Trainable Projection for Robust Fine-Tuning

• 论文地址：https://arxiv.org//pdf/2310.19182

• 开源代码：https://github.com/GT-RIPL/FTP

2.【基础网络架构：Transformer】TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic  Token Mixer for Visual Recognition

• 论文地址：https://arxiv.org//pdf/2310.19380

• 开源代码（即将开源）：https://github.com/LMMMEng/TransXNet

3.【图像分类】（NeurIPS2023）Analyzing Vision Transformers for Image Classification in Class  Embedding Space

• 论文地址：https://arxiv.org//pdf/2310.18969

• 开源代码：https://github.com/martinagvilas/vit-cls_emb

4.【目标检测】RGB-X Object Detection via Scene-Specific Fusion Modules

• 论文地址：https://arxiv.org//pdf/2310.19372

• 开源代码：https://github.com/dsriaditya999/RGBXFusion

5.【目标检测】A High-Resolution Dataset for Instance Detection with Multi-View  Instance Capture

• 论文地址：https://arxiv.org//pdf/2310.19257

• 开源代码：https://github.com/insdet/instance-detection

6.【目标检测】PrObeD: Proactive Object Detection Wrapper

• 论文地址：https://arxiv.org//pdf/2310.18788

• 开源代码（即将开源）：https://github.com/vishal3477/Proactive-Object-Detection#proactive-object-detection

7.【异常检测】Myriad: Large Multimodal Model by Applying Vision Experts for Industrial  Anomaly Detection

• 论文地址：https://arxiv.org//pdf/2310.19070

• 开源代码（即将开源）：https://github.com/tzjtatata/Myriad

8.【异常检测】AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly  Detection

• 论文地址：https://arxiv.org//pdf/2310.18961

• 开源代码（即将开源）：https://github.com/zqhang/AnomalyCLIP

9.【语义分割】（NeurIPS2023）Revisiting Evaluation Metrics for Semantic Segmentation: Optimization  and Evaluation of Fine-grained Intersection over Union

• 论文地址：https://arxiv.org//pdf/2310.19252

• 开源代码：https://github.com/zifuwanggg/JDTLosses

10.【语义分割】（NeurIPS2023）Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

• 论文地址：https://arxiv.org//pdf/2310.18640

• 开源代码（即将开源）：https://github.com/naver-ai/dual-teacher

11.【Open-Vocabulary Segmentation】（NeurIPS2023）Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic  Segmentation

• 论文地址：https://arxiv.org//pdf/2310.19001

• 开源代码（即将开源）：https://github.com/Ferenas/PGSeg

12.【视频语义分割】（NeurIPS2023）Mask Propagation for Efficient Video Semantic Segmentation

• 论文地址：https://arxiv.org//pdf/2310.18954

• 开源代码（即将开源）：https://github.com/ziplab/MPVSS

13.【超分辨率重建】（NeurIPS2023）Efficient Test-Time Adaptation for Super-Resolution with Second-Order  Degradation and Reconstruction

• 论文地址：https://arxiv.org//pdf/2310.19011

• 开源代码（即将开源）：https://github.com/DengZeshuai/SRTTA

14.【超分辨率重建】EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing  Image Super-Resolution

• 论文地址：https://arxiv.org//pdf/2310.19288

• 开源代码（即将开源）：https://github.com/XY-boy/EDiffSR

15.【领域泛化】（NeurIPS2023）SimMMDG: A Simple and Effective Framework for Multi-modal Domain  Generalization

• 论文地址：https://arxiv.org//pdf/2310.19795

• 开源代码（即将开源）：https://github.com/donghao51/SimMMDG

16.【领域泛化】（WACV2024）Domain Generalisation via Risk Distribution Matching

• 论文地址：https://arxiv.org//pdf/2310.18598

• 开源代码：https://github.com/nktoan/risk-distribution-matching

17.【多模态】Harvest Video Foundation Models via Efficient Post-Pretraining

• 论文地址：https://arxiv.org//pdf/2310.19554

• 开源代码：https://github.com/OpenGVLab/InternVideo

18.【多模态】IterInv: Iterative Inversion for Pixel-Level T2I Models

• 论文地址：https://arxiv.org//pdf/2310.19540

• 开源代码（即将开源）：https://github.com/Tchuanm/IterInv

19.【多模态】Generating Context-Aware Natural Answers for Questions in 3D Scenes

• 论文地址：https://arxiv.org//pdf/2310.19516

• 开源代码（即将开源）：https://github.com/MunzerDw/Gen3DQA

20.【多模态】Text-to-3D with Classifier Score Distillation

• 论文地址：https://arxiv.org//pdf/2310.19415

• 工程主页：https://xinyu-andy.github.io/Classifier-Score-Distillation/

• 代码即将开源

21.【多模态】Dynamic Task and Weight Prioritization Curriculum Learning for  Multimodal Imagery

• 论文地址：https://arxiv.org//pdf/2310.19109

• 开源代码：https://github.com/fualsan/DATWEP

22.【多模态】TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language  Understanding

• 论文地址：https://arxiv.org//pdf/2310.19060

• 开源代码：https://github.com/RenShuhuai-Andy/TESTA

23.【多模态】Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models

• 论文地址：https://arxiv.org//pdf/2310.18840

• 开源代码：https://github.com/littlewhitesea/StitchDiffusion

24.【多模态】ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond  Visual Common Sense

• 论文地址：https://arxiv.org//pdf/2310.19301

• 开源代码（即将开源）：https://github.com/K-Square-00/ROME

25.【多模态】Apollo: Zero-shot MultiModal Reasoning with Multiple Experts

• 论文地址：https://arxiv.org//pdf/2310.18369

• 开源代码：https://github.com/danielabd/Apollo-Cap

26.【自监督学习】Local-Global Self-Supervised Visual Representation Learning

• 论文地址：https://arxiv.org//pdf/2310.18651

• 开源代码：https://github.com/alijavidani/Local_Global_Representation_Learning

27.【自监督学习】（NeurIPS2023）InstanT: Semi-supervised Learning with Instance-dependent Thresholds

• 论文地址：https://arxiv.org//pdf/2310.18910

• 开源代码（即将开源）：https://github.com/tmllab/2023_NeurIPS_InstanT

28.【单目3D目标检测】ODM3D: Alleviating Foreground Sparsity for Enhanced Semi-Supervised  Monocular 3D Object Detection

• 论文地址：https://arxiv.org//pdf/2310.18620

• 开源代码（即将开源）：https://github.com/arcaninez/odm3d

29.【自动驾驶：协同感知】Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision

• 论文地址：https://arxiv.org//pdf/2310.19113

• 开源代码（即将开源）：https://github.com/tjy1423317192/AP2VP

30.【自动驾驶：深度估计】（NeurIPS2023）Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

• 论文地址：https://arxiv.org//pdf/2310.18887

• 工程主页：https://dynamo-depth.github.io/

• 开源代码（即将开源）：https://github.com/YihongSun/Dynamo-Depth

31.【图像编辑】（EMNLP2023）Learning to Follow Object-Centric Image Editing Instructions Faithfully

• 论文地址：https://arxiv.org//pdf/2310.19145

• 开源代码：https://github.com/tuhinjubcse/FaithfulEdits_EMNLP2023

32.【视频生成】VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

• 论文地址：https://arxiv.org//pdf/2310.19512

• 工程主页：https://ailab-cvc.github.io/videocrafter/

• 开源代码：https://github.com/AILab-CVC/VideoCrafter

33.【知识蒸馏】One-for-All: Bridge the Gap Between Heterogeneous Architectures in  Knowledge Distillation

• 论文地址：https://arxiv.org//pdf/2310.19444

• 开源代码：https://github.com/Hao840/OFAKD

34.【Continual Learning】（NeurIPS2023）NPCL: Neural Processes for Uncertainty-Aware Continual Learning

• 论文地址：https://arxiv.org//pdf/2310.19272

• 开源代码（即将开源）：https://github.com/srvCodes/NPCL

推荐阅读：

[1]读研期间，如何快速上手计算机视觉？

[2]23篇YOLO目标检测论文及代码分享

[3]Vision Transformer近三年18篇论文和代码分享

[4]人体姿态估计2023年最新论文和开源代码汇总（上）

[5]5分钟搞定深度学习中间特征可视化

[6]无监督视频实例分割新方法VideoCutLER！猛猛涨点！

[7]RevColV2：视觉预训练模型涨点！旷视提出将解耦表征应用于视觉预训练模型

[8]ICLR2023|解耦表征提升CNN和ViT性能！旷视等提出

[9]ICCV2023|涨点神器！目标检测蒸馏学习新方法，浙大、海康威视等提出

[10]EViT：借鉴鹰眼视觉结构，南开大学等提出ViT新骨干架构，在多个任务上涨点

[11]HSN：微调预训练ViT用于目标检测和分割的新方法，华南理工和阿里巴巴联合提出

[12]港科大提出适用于夜间场景语义分割的无监督域自适应新方法

[13]2023年9月-10月最新4篇带有开源代码的图像增强论文

[14]图像分类任务ViT与CNN谁更胜一筹？DeepMind用实验证明

[15]YOLO目标检测器中间特征可视化代码