paper-with-me

홈 › Papers

Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing

2020-09-30 · Okan Köpüklü, Stefan Hörmann, Fabian Herzog, Hakan Cevikalp, Gerhard Rigoll

Convolutional Neural Networks with 3D kernels (3D-CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames. There have been many successful 3D-CNN architectures surpassing the state-of-the-art results successively. However, nearly all of them are designed to operate offline creating several serious handicaps during online operation. Firstly, conventional 3D-CNNs are not dynamic since their output features represent the complete input clip instead of the most recent frame in the clip. Secondly, they are not temporal resolution-preserving due to their inherent temporal downsampling. Lastly, 3D-CNNs are constrained to be used with fixed temporal input size limiting their flexibility. In order to address these drawbacks, we propose dissected 3D-CNNs, where the intermediate volumes of the network are dissected and propagated over depth (time) dimension for future calculations, substantially reducing the number of computations at online operation. For action classification, the dissected version of ResNet models performs 77-90% fewer computations at online operation while achieving ~5% better classification accuracy on the Kinetics-600 dataset than conventional 3D-ResNet models. Moreover, the advantages of dissected 3D-CNNs are demonstrated by deploying our approach onto several vision tasks, which consistently improved the performance.

📄 PDF Abstract BibTeX arXiv:2009.14639

Code (1)

okankop/Dissected-3D-CNNs 공식 구현 pytorch

Tasks

Action ClassificationVideo Recognition

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Algebraic Representations for Faster Predictions in Convolutional Neural Networks

2024-08-14 · Johnny Joyce, Jan Verschelde

Convolutional neural networks (CNNs) are a popular choice of model for tasks in computer vision. When CNNs are made with many layers, resulting in a deep neural network, skip connections may be added to create an easier …

Always Skip Attention

2025-05-04 · Yiping Ji, Hemanth Saratchandran, Peyman Moghaddam, Simon Lucey

We highlight a curious empirical result within modern Vision Transformers (ViTs). Specifically, self-attention catastrophically fails to train unless it is used in conjunction with a skip connection. This is in contrast …

On the Vulnerability of Skip Connections to Model Inversion Attacks

2024-09-03 · Jun Hao Koh, Sy-Tuyen Ho, Ngoc-Bao Nguyen, Ngai-Man Cheung

Skip connections are fundamental architecture designs for modern deep neural networks (DNNs) such as CNNs and ViTs. While they help improve model performance significantly, we identify a vulnerability associated with ski…

LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections

2024-10-14 · Xuezhi Xiang, Yibo Ning, Lei Zhang, Denis Ombati 외

Semantic segmentation of remote sensing images is a fundamental task in geospatial research. However, widely used Convolutional Neural Networks (CNNs) and Transformers have notable drawbacks: CNNs may be limited by insuf…

DecoderSemantic Segmentation

How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?

2019-10-02 · CVPR 2021 1 · Kartikeya Bhardwaj, Guihong Li, Radu Marculescu

DenseNets introduce concatenation-type skip connections that achieve state-of-the-art accuracy in several computer vision tasks. In this paper, we reveal that the topology of the concatenation-type skip connections is cl…

Model Compression