Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution
- URL: http://arxiv.org/abs/2006.12085v1
- Date: Mon, 22 Jun 2020 09:08:51 GMT
- Title: Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution
- Authors: Qiulin Zhang, Zhuqing Jiang, Qishuo Lu, Jia'nan Han, Zhengxin Zeng,
Shang-hua Gao, Aidong Men
- Abstract summary: We propose a textbfsplit based textbfconvolutional operation, namely SPConv, to tolerate features with similar patterns but require less computation.
We show that SPConv-equipped networks consistently outperform state-of-the-art baselines in both accuracy and inference time on GPU.
- Score: 11.674837640798126
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many effective solutions have been proposed to reduce the redundancy of
models for inference acceleration. Nevertheless, common approaches mostly focus
on eliminating less important filters or constructing efficient operations,
while ignoring the pattern redundancy in feature maps. We reveal that many
feature maps within a layer share similar but not identical patterns. However,
it is difficult to identify if features with similar patterns are redundant or
contain essential details. Therefore, instead of directly removing uncertain
redundant features, we propose a \textbf{sp}lit based \textbf{conv}olutional
operation, namely SPConv, to tolerate features with similar patterns but
require less computation. Specifically, we split input feature maps into the
representative part and the uncertain redundant part, where intrinsic
information is extracted from the representative part through relatively heavy
computation while tiny hidden details in the uncertain redundant part are
processed with some light-weight operation. To recalibrate and fuse these two
groups of processed features, we propose a parameters-free feature fusion
module. Moreover, our SPConv is formulated to replace the vanilla convolution
in a plug-and-play way. Without any bells and whistles, experimental results on
benchmarks demonstrate SPConv-equipped networks consistently outperform
state-of-the-art baselines in both accuracy and inference time on GPU, with
FLOPs and parameters dropped sharply.
Related papers
- A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.
We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.
We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
arXiv Detail & Related papers (2024-07-02T14:12:21Z) - Single image super-resolution based on trainable feature matching attention network [0.0]
Convolutional Neural Networks (CNNs) have been widely employed for image Super-Resolution (SR)
We introduce Trainable Feature Matching (TFM) to amalgamate explicit feature learning into CNNs, augmenting their representation capabilities.
We also propose a streamlined variant called Same-size-divided Region-level Non-Local (SRNL) to alleviate the computational demands of non-local operations.
arXiv Detail & Related papers (2024-05-29T08:31:54Z) - On Unsupervised Partial Shape Correspondence [9.175560202201819]
We argue that functional maps introduce errors in the estimated match when partiality is invoked.
We propose a novel approach for partial shape matching.
The proposed approach shows superior performance on the SHREC'16 dataset.
arXiv Detail & Related papers (2023-10-23T08:32:50Z) - PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute
Recognition [23.814762073093153]
We propose a pure transformer-based multi-task PAR network named PARFormer, which includes four modules.
In the feature extraction module, we build a strong baseline for feature extraction, which achieves competitive results on several PAR benchmarks.
In the viewpoint perception module, we explore the impact of viewpoints on pedestrian attributes, and propose a multi-view contrastive loss.
In the attribute recognition module, we alleviate the negative-positive imbalance problem to generate the attribute predictions.
arXiv Detail & Related papers (2023-04-14T16:27:56Z) - Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo
Matching Networks [3.7384509727711923]
We introduce a pairwise feature for deep stereo matching networks, named LSP (Local Similarity Pattern)
Through explicitly revealing the neighbor relationships, LSP contains rich structural information, which can be leveraged to aid for more discriminative feature description.
Secondly, we design a dynamic self-reassembling refinement strategy and apply it to the cost distribution and the disparity map respectively.
arXiv Detail & Related papers (2021-12-02T06:52:54Z) - PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result.
Recent transformer-based image recognition model andTT show consistent efficiency gain.
arXiv Detail & Related papers (2021-09-15T01:10:30Z) - A^2-FPN: Attention Aggregation based Feature Pyramid Network for
Instance Segmentation [68.10621089649486]
We propose Attention Aggregation based Feature Pyramid Network (A2-FPN) to improve multi-scale feature learning.
A2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.
arXiv Detail & Related papers (2021-05-07T11:51:08Z) - Manifold Regularized Dynamic Network Pruning [102.24146031250034]
This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks.
The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
arXiv Detail & Related papers (2021-03-10T03:59:03Z) - GhostSR: Learning Ghost Features for Efficient Image Super-Resolution [49.393251361038025]
Single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs.
We propose to use shift operation to generate the redundant features (i.e., Ghost features) of SISR models.
We show that both the non-compact and lightweight SISR models embedded in our proposed module can achieve comparable performance to that of their baselines.
arXiv Detail & Related papers (2021-01-21T10:09:47Z) - Spatially Adaptive Inference with Stochastic Feature Sampling and
Interpolation [72.40827239394565]
We propose to compute features only at sparsely sampled locations.
We then densely reconstruct the feature map with an efficient procedure.
The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
arXiv Detail & Related papers (2020-03-19T15:36:31Z)
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.