Attention in Attention Network for Image Super-Resolution
- URL: http://arxiv.org/abs/2104.09497v1
- Date: Mon, 19 Apr 2021 17:59:06 GMT
- Title: Attention in Attention Network for Image Super-Resolution
- Authors: Haoyu Chen, Jinjin Gu, Zhi Zhang
- Abstract summary: We quantify and visualize the static attention mechanisms and show that not all attention modules are equally beneficial.
We propose attention in attention network (A$2$N) for highly accurate image SR.
Our model could achieve superior trade-off performances comparing with state-of-the-art lightweight networks.
- Score: 18.2279472158217
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Convolutional neural networks have allowed remarkable advances in single
image super-resolution (SISR) over the last decade. Among recent advances in
SISR, attention mechanisms are crucial for high performance SR models. However,
few works really discuss why attention works and how it works. In this work, we
attempt to quantify and visualize the static attention mechanisms and show that
not all attention modules are equally beneficial. We then propose attention in
attention network (A$^2$N) for highly accurate image SR. Specifically, our
A$^2$N consists of a non-attention branch and a coupling attention branch.
Attention dropout module is proposed to generate dynamic attention weights for
these two branches based on input features that can suppress unwanted attention
adjustments. This allows attention modules to specialize to beneficial examples
without otherwise penalties and thus greatly improve the capacity of the
attention network with little parameter overhead. Experiments have demonstrated
that our model could achieve superior trade-off performances comparing with
state-of-the-art lightweight networks. Experiments on local attribution maps
also prove attention in attention (A$^2$) structure can extract features from a
wider range.
Related papers
- CiaoSR: Continuous Implicit Attention-in-Attention Network for
Arbitrary-Scale Image Super-Resolution [158.2282163651066]
This paper proposes a continuous implicit attention-in-attention network, called CiaoSR.
We explicitly design an implicit attention network to learn the ensemble weights for the nearby local features.
We embed a scale-aware attention in this implicit attention network to exploit additional non-local information.
arXiv Detail & Related papers (2022-12-08T15:57:46Z) - Efficient Image Super-Resolution using Vast-Receptive-Field Attention [49.87316814164699]
The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks.
In this work, we design an efficient SR network by improving the attention mechanism.
We propose VapSR, the VAst-receptive-field Pixel attention network.
arXiv Detail & Related papers (2022-10-12T07:01:00Z) - Switchable Self-attention Module [3.8992324495848356]
We propose a self-attention module SEM.
Based on the input information of the attention module and alternative attention operators, SEM can automatically decide to select and integrate attention operators to compute attention maps.
The effectiveness of SEM is demonstrated by extensive experiments on widely used benchmark datasets and popular self-attention networks.
arXiv Detail & Related papers (2022-09-13T01:19:38Z) - Self-Supervised Implicit Attention: Guided Attention by The Model Itself [1.3406858660972554]
We propose Self-Supervised Implicit Attention (SSIA), a new approach that adaptively guides deep neural network models to gain attention by exploiting the properties of the models themselves.
SSIAA is a novel attention mechanism that does not require any extra parameters, computation, or memory access costs during inference.
Our implementation will be available on GitHub.
arXiv Detail & Related papers (2022-06-15T10:13:34Z) - Visual Attention Network [90.0753726786985]
We propose a novel large kernel attention (LKA) module to enable self-adaptive and long-range correlations in self-attention.
We also introduce a novel neural network based on LKA, namely Visual Attention Network (VAN)
VAN outperforms the state-of-the-art vision transformers and convolutional neural networks with a large margin in extensive experiments.
arXiv Detail & Related papers (2022-02-20T06:35:18Z) - Learning to ignore: rethinking attention in CNNs [87.01305532842878]
We propose to reformulate the attention mechanism in CNNs to learn to ignore instead of learning to attend.
Specifically, we propose to explicitly learn irrelevant information in the scene and suppress it in the produced representation.
arXiv Detail & Related papers (2021-11-10T13:47:37Z) - Coordinate Attention for Efficient Mobile Network Design [96.40415345942186]
We propose a novel attention mechanism for mobile networks by embedding positional information into channel attention.
Unlike channel attention that transforms a feature tensor to a single feature vector via 2D global pooling, the coordinate attention factorizes channel attention into two 1D feature encoding processes.
Our coordinate attention is beneficial to ImageNet classification and behaves better in down-stream tasks, such as object detection and semantic segmentation.
arXiv Detail & Related papers (2021-03-04T09:18:02Z) - Unlocking Pixels for Reinforcement Learning via Implicit Attention [61.666538764049854]
We make use of new efficient attention algorithms, recently shown to be highly effective for Transformers.
This allows our attention-based controllers to scale to larger visual inputs, and facilitate the use of smaller patches.
In addition, we propose a new efficient algorithm approximating softmax attention with what we call hybrid random features.
arXiv Detail & Related papers (2021-02-08T17:00:26Z) - Efficient Attention Network: Accelerate Attention by Searching Where to
Plug [11.616720452770322]
We propose a framework called Efficient Attention Network (EAN) to improve the efficiency for the existing attention modules.
In EAN, we leverage the sharing mechanism to share the attention module within the backbone and search where to connect the shared attention module via reinforcement learning.
Experiments on widely-used benchmarks and popular attention networks show the effectiveness of EAN.
arXiv Detail & Related papers (2020-11-28T03:31:08Z) - Attention-Guided Network for Iris Presentation Attack Detection [13.875545441867137]
We propose attention-guided iris presentation attack detection (AG-PAD) to augment CNNs with attention mechanisms.
Experiments involving both a JHU-APL proprietary dataset and the benchmark LivDet-Iris-2017 dataset suggest that the proposed method achieves promising results.
arXiv Detail & Related papers (2020-10-23T19:23:51Z)
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.