paper-with-me

Papers

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

2020-04-10 · Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh

How can we collect and use a video dataset to further improve spatiotemporal 3D Convolutional Neural Networks (3D CNNs)? In order to positively answer this open question in video recognition, we have conducted an exploration study using a couple of large-scale video datasets and 3D CNNs. In the early era of deep neural networks, 2D CNNs have been better than 3D CNNs in the context of video recognition. Recent studies revealed that 3D CNNs can outperform 2D CNNs trained on a large-scale video dataset. However, we heavily rely on architecture exploration instead of dataset consideration. Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy. We reveal that a carefully annotated dataset (e.g., Kinetics-700) effectively pre-trains a video representation for a video classification task. (ii) We confirm the relationships between #category/#instance and video classification accuracy. The results show that #category should initially be fixed, and then #instance is increased on a video dataset in case of dataset construction. (iii) In order to practically extend a video dataset, we simply concatenate publicly available datasets, such as Kinetics-700 and Moments in Time (MiT) datasets. Compared with Kinetics-700 pre-training, we further enhance spatiotemporal 3D CNNs with the merged dataset, e.g., +0.9, +3.4, and +1.1 on UCF-101, HMDB-51, and ActivityNet datasets, respectively, in terms of fine-tuning. (iv) In terms of recognition architecture, the Kinetics-700 and merged dataset pre-trained models increase the recognition performance to 200 layers with the Residual Network (ResNet), while the Kinetics-400 pre-trained model cannot successfully optimize the 200-layer architecture.

📄 PDF Abstract BibTeX arXiv:2004.04968

Code (10)

kenshohara/3D-ResNets-PyTorch 공식 구현 pytorch
3D-ResNets-Reproduction/Reference-Project pytorch
KevinPang180/3D-ResNets-PaddlePaddle pytorch
Mind23-2/MindCode-68 mindspore
Oichii/resnet3D_pulse pytorch
Shito0907/3D_resnet pytorch
kaleab-k/VideoAT pytorch
mindspore-ai/models/tree/master/research/cv/resnet3d mindspore
rutajoshi/cs231n-project pytorch
ziqi-zhang/3D-ResNets-PyTorch pytorch

Tasks

General ClassificationOpen-Ended Question AnsweringVideo ClassificationVideo Recognition

Similar Papers 제목 키워드 기반

An Efficient 2D Method for Training Super-Large Deep Learning Models

2021-04-12 · Qifan Xu, Shenggui Li, Chaoyu Gong, Yang You

Huge neural network models have shown unprecedented performance in real-world applications. However, due to memory constraints, model parallelism must be utilized to host large models that would otherwise not fit into th…

MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism

2025-04-03 · Ruidong Zhu, Ziheng Jiang, Chao Jin, Peng Wu 외

Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely activated architecture shifts feed-forwa…

CPUGPUMixture-of-Experts

Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs

2021-12-20 · CVPR 2022 1 · Haithem Turki, Deva Ramanan, Mahadev Satyanarayanan

We use neural radiance fields (NeRFs) to build interactive 3D environments from large-scale visual captures spanning buildings or even multiple city blocks collected primarily from drones. In contrast to single object sc…

GPUNeRF

MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production

2025-05-16 · Chao Jin, Ziheng Jiang, Zhihao Bai, Zheng Zhong 외

We present MegaScale-MoE, a production system tailored for the efficient training of large-scale mixture-of-experts (MoE) models. MoE emerges as a promising architecture to scale large language models (LLMs) to unprecede…

Mixture-of-Experts

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

2025-07-22 · Run-Ze Fan, Zengzhi Wang, Pengfei Liu arxiv

Scientific reasoning is critical for developing AI scientists and supporting human researchers in advancing the frontiers of natural science discovery. However, the open-source community has primarily focused on mathemat…