语言大模型 / LLM - arXivDaily 专题

2211.05778 2023-04-18 cs.CV 78%

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Wenhai Wang, Jifeng Dai, Zhe Chen, Zhenhang Huang, Zhiqi Li, Xizhou Zhu, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, Xiaogang Wang, Yu Qiao

专题命中预训练与数据：foundation model(title,abstract)

Comments Accepted to CVPR 2023

2208.12262 2023-04-11 cs.CV 78%

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

Xiaoyi Dong, Jianmin Bao, Yinglin Zheng, Ting Zhang, Dongdong Chen, Hao Yang, Ming Zeng, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, Nenghai Yu

专题命中预训练与数据：pretraining(title,abstract)

Comments CVPR 2023, code is available at https://github.com/LightDXY/MaskCLIP

2304.03105 2023-04-10 cs.CV 78%

Geometric-aware Pretraining for Vision-centric 3D Object Detection

Linyan Huang, Huijie Wang, Jia Zeng, Shengchuan Zhang, Liujuan Cao, Junchi Yan, Hongyang Li

专题命中预训练与数据：pretraining(title,abstract)

Comments 15 pages, 3 figures

2212.05051 2023-04-06 cs.CV 78%

VindLU: A Recipe for Effective Video-and-Language Pretraining

Feng Cheng, Xizi Wang, Jie Lei, David Crandall, Mohit Bansal, Gedas Bertasius

专题命中预训练与数据：pretraining(title,abstract)

Comments CVPR 2023. Project page: https://klauscc.github.io/vindlu.html

2303.17636 2023-04-03 cs.CV 78%

Whether and When does Endoscopy Domain Pretraining Make Sense?

Dominik Batić, Felix Holm, Ege Özsoy, Tobias Czempiel, Nassir Navab

专题命中预训练与数据：pretraining(title,abstract)

2303.05675 2023-03-13 cs.CV 78%

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted to CVPR2023

2303.01237 2023-03-03 cs.CV 78%

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Xiaoyu Shi, Zhaoyang Huang, Dasong Li, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li

专题命中预训练与数据：pretraining(title,abstract)

2111.13675 2023-02-07 cs.CV 78%

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

Kumara Kahatapitiya, Zhou Ren, Haoxiang Li, Zhenyu Wu, Michael S. Ryoo, Gang Hua

专题命中预训练与数据：pretraining(title,abstract)

Comments Published as a conference paper at AAAI 2023

2302.01384 2023-02-06 cs.CV 78%

Energy-Inspired Self-Supervised Pretraining for Vision Models

Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu

专题命中预训练与数据：pretraining(title,abstract)

Journal ref ICLR 2023

2110.05074 2022-12-29 cs.CV 78%

Rethinking Person Re-Identification via Semantic-Based Pretraining

Suncheng Xiang, Jingsheng Gao, Zirui Zhang, Mengyuan Guan, Binjie Yan, Ting Liu, Dahong Qian, Yuzhuo Fu

专题命中预训练与数据：pretraining(title,abstract)

2209.13558 2022-12-15 cs.CV 78%

FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation

Yi Li, Huifeng Yao, Hualiang Wang, Xiaomeng Li

专题命中预训练与数据：pretraining(title,abstract)

Comments This paper contains some immature results

2207.11514 2022-12-07 cs.CV cs.RO 78%

Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models

Huy Ha, Shuran Song

专题命中预训练与数据：language model(title,abstract)

Comments 16 pages, 9 figures, project website at https://semantic-abstraction.cs.columbia.edu/

2211.15428 2022-11-29 cs.CV 78%

Explanation on Pretraining Bias of Finetuned Vision Transformer

Bumjin Park, Jaesik Choi

专题命中预训练与数据：pretraining(title,abstract)

2211.12931 2022-11-24 cs.CV 78%

Can we Adopt Self-supervised Pretraining for Chest X-Rays?

Arsh Verma, Makarand Tapaswi

专题命中预训练与数据：pretraining(title,abstract)

Comments Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 10 pages

2211.09927 2022-11-21 cs.CV eess.IV eess.SP 78%

SAR-based landslide classification pretraining leads to better segmentation

Vanessa Böhm, Wei Ji Leong, Ragini Bal Mahesh, Ioannis Prapas, Edoardo Nemni, Freddie Kalaitzis, Siddha Ganju, Raul Ramos-Pollan

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted to the NeurIPS 2022 workshop Artificial Intelligence for Humanitarian Assistance and Disaster Response. This research was conducted as part of the Frontier Development Lab (FDL) 2022

2211.03594 2022-11-08 cs.CV 78%

Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

Qiang Chen, Jian Wang, Chuchu Han, Shan Zhang, Zexian Li, Xiaokang Chen, Jiahui Chen, Xiaodi Wang, Shuming Han, Gang Zhang, Haocheng Feng, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

专题命中预训练与数据：pretraining(title,abstract)

Comments Tech report, 3 pages. We establishes a new SoTA (64.5 mAP) on the COCO test-dev

2210.04477 2022-10-14 cs.CV 78%

HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining

Chunhui Zhang, Yixiong Chen, Li Liu, Qiong Liu, Xi Zhou

专题命中预训练与数据：pretraining(title,abstract)

Comments Paper accepted in ACCV 2022

2207.03860 2022-09-15 cs.CV 78%

Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain

Tong Zhang, Peng Gao, Hao Dong, Yin Zhuang, Guanqun Wang, Wei Zhang, He Chen

专题命中预训练与数据：pretraining(title,abstract)

Comments 20 pages,9 figures

2208.11563 2022-08-25 eess.IV cs.CV q-bio.QM 78%

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

Minhaj Nur Alam, Rikiya Yamashita, Vignav Ramesh, Tejas Prabhune, Jennifer I. Lim, R. V. P. Chan, Joelle Hallak, Theodore Leng, Daniel Rubin

专题命中预训练与数据：pretraining(title,abstract)

2208.05838 2022-08-12 cs.CV 78%

Differencing based Self-supervised pretraining for Scene Change Detection

Vijaya Raghavan T. Ramkumar, Elahe Arani, Bahram Zonooz

专题命中预训练与数据：pretraining(title,abstract)

Comments Published at Conference on Lifelong Learning Agents (CoLLAs 2022)

2207.04186 2022-08-12 cs.CV 78%

A Study on Self-Supervised Object Detection Pretraining

Trung Dang, Simon Kornblith, Huy Thong Nguyen, Peter Chin, Maryam Khademi

专题命中预训练与数据：pretraining(title,abstract)

2208.04268 2022-08-09 cs.CV 78%

Label-Free Synthetic Pretraining of Object Detectors

Hei Law, Jia Deng

专题命中预训练与数据：pretraining(title,abstract)

2109.10504 2022-08-09 cs.CV 78%

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

Yongfei Liu, Chenfei Wu, Shao-yen Tseng, Vasudev Lal, Xuming He, Nan Duan

专题命中预训练与数据：pretraining(title,abstract)

2206.07125 2022-08-08 cs.CV cs.CR 78%

Self-Supervised Pretraining for Differentially Private Learning

Arash Asadian, Evan Weidner, Lei Jiang

专题命中预训练与数据：pretraining(title,abstract)

2203.14395 2022-07-29 cs.CV 78%

Single-Stream Multi-Level Alignment for Vision-Language Pretraining

Zaid Khan, Vijay Kumar BG, Xiang Yu, Samuel Schulter, Manmohan Chandraker, Yun Fu

专题命中预训练与数据：pretraining(title,abstract)

Comments ECCV 2022

2207.10666 2022-07-22 cs.CV 78%

TinyViT: Fast Pretraining Distillation for Small Vision Transformers

Kan Wu, Jinnian Zhang, Houwen Peng, Mengchen Liu, Bin Xiao, Jianlong Fu, Lu Yuan

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted by ECCV 2022

2207.08954 2022-07-20 cs.CV 78%

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, Vijay Kumar B. G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas

专题命中预训练与数据：language model(title,abstract)

Comments Accepted to ECCV 2022 (with the supplementary document)

2203.15431 2022-06-30 cs.SD eess.AS 78%

Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

Lester Phillip Violeta, Wen-Chin Huang, Tomoki Toda

专题命中预训练与数据：pretraining(title,abstract)

Comments Accepted to INTERSPEECH 2022

2206.11927 2022-06-27 cs.CV astro-ph.GA 78%

Towards Galaxy Foundation Models with Hybrid Contrastive Learning

Mike Walmsley, Inigo Val Slijepcevic, Micah Bowles, Anna M. M. Scaife

专题命中预训练与数据：foundation model(title)；pretraining(abstract)

Comments Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics. Data: www.github.com/mwalmsley/pytorch-galaxy-datasets. Please reach out to share your labelled data - all contributions will be credited in future work

2206.08842 2022-06-20 cs.MM cs.CV cs.DB cs.IR 78%

Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval

Xiao Dong, Xunlin Zhan, Yunchao Wei, Xiaoyong Wei, Yaowei Wang, Minlong Lu, Xiaochun Cao, Xiaodan Liang

专题命中预训练与数据：pretraining(title,abstract)

1. 预训练与数据 12393 篇

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

Geometric-aware Pretraining for Vision-centric 3D Object Detection

VindLU: A Recipe for Effective Video-and-Language Pretraining

Whether and When does Endoscopy Domain Pretraining Make Sense?

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

Energy-Inspired Self-Supervised Pretraining for Vision Models

Rethinking Person Re-Identification via Semantic-Based Pretraining

FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation

Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models

Explanation on Pretraining Bias of Finetuned Vision Transformer

Can we Adopt Self-supervised Pretraining for Chest X-Rays?

SAR-based landslide classification pretraining leads to better segmentation

Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining

Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

Differencing based Self-supervised pretraining for Scene Change Detection

A Study on Self-Supervised Object Detection Pretraining

Label-Free Synthetic Pretraining of Object Detectors

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

Self-Supervised Pretraining for Differentially Private Learning

Single-Stream Multi-Level Alignment for Vision-Language Pretraining

TinyViT: Fast Pretraining Distillation for Small Vision Transformers

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

Towards Galaxy Foundation Models with Hybrid Contrastive Learning

Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval