欢迎分享ICCV 2023 论文和代码 / Welcome to share the paper and code of ICCV 2023 about iccv2021-papers-with-code HOT 13 OPEN

Paper name/title: Femtodet: an object detection baseline for energy versus performance tradeoffs
Paper link: https://arxiv.org/pdf/2301.06719.pdf
Code link: https://github.com/yh-pengtu/FemtoDet
Thank you very very very very very very much!!!!!

from iccv2021-papers-with-code.

Related areas: Diffusion Models(扩散模型)
Paper name/title: BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
Paper link: https://arxiv.org/abs/2307.10816
Code link: https://github.com/Sierkinhane/BoxDiff
keywords: text-to-image synthesis, diffusion models, layout-to-image synthesis

from iccv2021-papers-with-code.

Paper name: SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
Paper link: https://arxiv.org/abs/2304.14340
Code link: https://github.com/yichen928/SparseFusion
Thank you very much!

from iccv2021-papers-with-code.

Paper name/title: Simulating Fluids in Real-World Still Images
Paper link: https://arxiv.org/abs/2204.11335
Code link: https://github.com/simon3dv/SLR-SFS
Project Page: https://slr-sfs.github.io/
Related areas: Video Generation
Thank you very much!

from iccv2021-papers-with-code.

Related areas: 3D Object Detection

Paper name/title: StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
Paper link: https://arxiv.org/pdf/2303.11926.pdf
Code link: https://github.com/exiawsh/StreamPETR.git

Paper name/title: Cross Modal Transformer: Towards Fast and Robust 3D Object Detection
Paper link: https://arxiv.org/pdf/2301.01283.pdf
Code link: https://github.com/junjie18/CMT.git

Thank you very much!

from iccv2021-papers-with-code.

Related areas: BEV Perception/3D Perception/Autonomy Perception

Paper name/title: MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
Paper link: https://arxiv.org/abs/2304.09801
Project link: https://chongjiange.github.io/metabev.html
Code link: https://github.com/ChongjianGE/MetaBEV

Thank you very much!

from iccv2021-papers-with-code.

Paper name/title: FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation
Paper link: https://arxiv.org/abs/2307.07245
Code link: https://github.com/TY-Shi/FreeCOS
keywords: self-supervised learning, segmentation

from iccv2021-papers-with-code.

Related Area: 3D Object Detection, Domain Adaptation
Paper title: Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Paper link: https://arxiv.org/abs/2307.07944
Code link: https://github.com/zhuoxiao-chen/ReDB-DA-3Ddet
Thank you very much!

from iccv2021-papers-with-code.

Paper name: CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection
Rank First in Medical Segmentation Decathlon (MSD) Competition
paper | code | slides | poster | talk

Thank you very much!

from iccv2021-papers-with-code.

Related Area: Anomaly Segmentation / Out-of-Distribution Segmentation
Paper name: Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Paper link: https://arxiv.org/pdf/2211.14512.pdf
Code link: https://github.com/yyliu01

Related Area: Multi-Label Noisy Label Learning
Paper name: BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Paper link: https://arxiv.org/pdf/2203.01937.pdf
Code link: https://github.com/cyh-0/BoMD

@amusi Thanks so much for your help.

from iccv2021-papers-with-code.

Related Area: CLIP, Prompt, Vision-Language, Domain Generalization
Paper name/title: PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Paper link: https://arxiv.org/abs/2307.15199
Project Page: https://PromptStyler.github.io/

@amusi
Thanks for your help!!

from iccv2021-papers-with-code.

Paper name: Denoising Diffusion Autoencoders are Unified Self-supervised Learners
Paper link: https://arxiv.org/abs/2303.09769
Code link: https://github.com/FutureXiang/ddae
Related area: Diffusion, Self-supervised representation learning

Selected for Oral presentation at ICCV 23.
@amusi Thank you!

from iccv2021-papers-with-code.

Paper name: On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
Paper link: https://arxiv.org/abs/2308.09942
Code link: https://github.com/Yushu-Li/OWTTT
Project Page: https://yushu-li.github.io/2023_LiEtAl_OWTTT/
Related area: Transfer Learning, Test-Time Adaptation

Selected for Oral presentation at ICCV 23.
@amusi Thank you!

from iccv2021-papers-with-code.