Skip-Convolutions for Efficient Video Processing
- URL: http://arxiv.org/abs/2104.11487v1
- Date: Fri, 23 Apr 2021 09:10:39 GMT
- Title: Skip-Convolutions for Efficient Video Processing
- Authors: Amirhossein Habibian, Davide Abati, Taco S. Cohen, Babak Ehteshami
Bejnordi
- Abstract summary: Skip-Convolutions leverage the large amount of redundancies in video streams and save computations.
We replace all convolutions with Skip-Convolutions in two state-of-the-art architectures, namely EfficientDet and HRNet.
We reduce their computational cost consistently by a factor of 34x for two different tasks, without any accuracy drop.
- Score: 21.823332885657784
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose Skip-Convolutions to leverage the large amount of redundancies in
video streams and save computations. Each video is represented as a series of
changes across frames and network activations, denoted as residuals. We
reformulate standard convolution to be efficiently computed on residual frames:
each layer is coupled with a binary gate deciding whether a residual is
important to the model prediction,~\eg foreground regions, or it can be safely
skipped, e.g. background regions. These gates can either be implemented as an
efficient network trained jointly with convolution kernels, or can simply skip
the residuals based on their magnitude. Gating functions can also incorporate
block-wise sparsity structures, as required for efficient implementation on
hardware platforms. By replacing all convolutions with Skip-Convolutions in two
state-of-the-art architectures, namely EfficientDet and HRNet, we reduce their
computational cost consistently by a factor of 3~4x for two different tasks,
without any accuracy drop. Extensive comparisons with existing model
compression, as well as image and video efficiency methods demonstrate that
Skip-Convolutions set a new state-of-the-art by effectively exploiting the
temporal redundancies in videos.
Related papers
- SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity [15.872209884833977]
We propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation.
SparseTem achieves speedup of 1.79x for EfficientDet and 4.72x for CRNN, with minimal accuracy drop and no additional memory overhead.
arXiv Detail & Related papers (2024-10-28T07:13:25Z) - Signed Binarization: Unlocking Efficiency Through Repetition-Sparsity
Trade-Off [2.6144163646666945]
This paper introduces the concept of repetition-sparsity trade-off that helps explain computational efficiency during inference.
We propose Signed Binarization, a unified co-design framework that integrates hardware-software systems, quantization functions, and representation learning techniques to address this trade-off.
Our approach achieves a 26% speedup on real hardware, doubles energy efficiency, and reduces density by 2.8x compared to binary methods for ResNet 18.
arXiv Detail & Related papers (2023-12-04T02:33:53Z) - Dynamic Frame Interpolation in Wavelet Domain [57.25341639095404]
Video frame is an important low-level computation vision task, which can increase frame rate for more fluent visual experience.
Existing methods have achieved great success by employing advanced motion models and synthesis networks.
WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.
arXiv Detail & Related papers (2023-09-07T06:41:15Z) - ReBotNet: Fast Real-time Video Enhancement [59.08038313427057]
Most restoration networks are slow, have high computational bottleneck, and can't be used for real-time video enhancement.
In this work, we design an efficient and fast framework to perform real-time enhancement for practical use-cases like live video calls and video streams.
To evaluate our method, we emulate two new datasets that real-world video call and streaming scenarios, and show extensive results on multiple datasets where ReBotNet outperforms existing approaches with lower computations, reduced memory requirements, and faster inference time.
arXiv Detail & Related papers (2023-03-23T17:58:05Z) - Deep Unsupervised Key Frame Extraction for Efficient Video
Classification [63.25852915237032]
This work presents an unsupervised method to retrieve the key frames, which combines Convolutional Neural Network (CNN) and Temporal Segment Density Peaks Clustering (TSDPC)
The proposed TSDPC is a generic and powerful framework and it has two advantages compared with previous works, one is that it can calculate the number of key frames automatically.
Furthermore, a Long Short-Term Memory network (LSTM) is added on the top of the CNN to further elevate the performance of classification.
arXiv Detail & Related papers (2022-11-12T20:45:35Z) - TVConv: Efficient Translation Variant Convolution for Layout-aware
Visual Processing [10.996162201540695]
We develop efficient translation variant convolution (TVConv) for layout-aware visual processing.
TVConv significantly improves the efficiency of the convolution and can be readily plugged into various network architectures.
arXiv Detail & Related papers (2022-03-20T08:29:06Z) - Content-Aware Convolutional Neural Networks [98.97634685964819]
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers.
We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
arXiv Detail & Related papers (2021-06-30T03:54:35Z) - Adaptive Focus for Efficient Video Recognition [29.615394426035074]
We propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus)
A light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions.
During offline inference, once the informative patch sequence has been generated, the bulk of computation can be done in parallel, and is efficient on modern GPU devices.
arXiv Detail & Related papers (2021-05-07T13:24:47Z) - VA-RED$^2$: Video Adaptive Redundancy Reduction [64.75692128294175]
We present a redundancy reduction framework, VA-RED$2$, which is input-dependent.
We learn the adaptive policy jointly with the network weights in a differentiable way with a shared-weight mechanism.
Our framework achieves $20% - 40%$ reduction in computation (FLOPs) when compared to state-of-the-art methods.
arXiv Detail & Related papers (2021-02-15T22:57:52Z) - Structured Convolutions for Efficient Neural Network Design [65.36569572213027]
We tackle model efficiency by exploiting redundancy in the textitimplicit structure of the building blocks of convolutional neural networks.
We show how this decomposition can be applied to 2D and 3D kernels as well as the fully-connected layers.
arXiv Detail & Related papers (2020-08-06T04:38:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.