Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

• URL: http://arxiv.org/abs/2110.11852v1
• Date: Fri, 22 Oct 2021 15:36:33 GMT
• Title: Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Authors: Jingyu Zhao, Yanwen Fang and Guodong Li
• Abstract summary: This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. We propose a very light-weighted module, called recurrent layer aggregation (RLA), by making use of the sequential structure of layers in a deep CNN. Our RLA module is compatible with many mainstream deep CNNs, including ResNets, Xception and MobileNetV2.
• Score: 5.71305698739856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. While DenseNet is a typical example of the layer aggregation mechanism, its redundancy has been commonly criticized in the literature. This motivates us to propose a very light-weighted module, called recurrent layer aggregation (RLA), by making use of the sequential structure of layers in a deep CNN. Our RLA module is compatible with many mainstream deep CNNs, including ResNets, Xception and MobileNetV2, and its effectiveness is verified by our extensive experiments on image classification, object detection and instance segmentation tasks. Specifically, improvements can be uniformly observed on CIFAR, ImageNet and MS COCO datasets, and the corresponding RLA-Nets can surprisingly boost the performances by 2-3% on the object detection task. This evidences the power of our RLA module in helping main CNNs better learn structural information in images.

Related papers

• Scale-Invariant Object Detection by Adaptive Convolution with Unified Global-Local Context [3.061662434597098]
  We propose an object detection model using a Switchable (adaptive) Atrous Convolutional Network (SAC-Net) based on the efficientDet model. The proposed SAC-Net encapsulates the benefits of both low-level and high-level features to achieve improved performance on multi-scale object detection tasks. Our experiments on benchmark datasets demonstrate that the proposed SAC-Net outperforms the state-of-the-art models by a significant margin in terms of accuracy.
  arXiv  Detail & Related papers  (2024-09-17T10:08:37Z)
• SENetV2: Aggregated dense layer for channelwise and global representations [0.0]
  We introduce a novel aggregated multilayer perceptron, a multi-branch dense layer, within the Squeeze residual module. This fusion enhances the network's ability to capture channel-wise patterns and have global knowledge. We conduct extensive experiments on benchmark datasets to validate the model and compare them with established architectures.
  arXiv  Detail & Related papers  (2023-11-17T14:10:57Z)
• Designing Deep Networks for Scene Recognition [3.493180651702109]
  We conduct extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences when the data is altered. This paper presents a novel network design methodology: data-oriented network design. We propose a Deep-Narrow Network and Dilated Pooling module, which improved the scene recognition performance using less than half of the computational resources.
  arXiv  Detail & Related papers  (2023-03-13T18:28:06Z)
• Cross-Layer Retrospective Retrieving via Layer Attention [12.423426718300151]
  We devise a cross-layer attention mechanism called multi-head recurrent layer attention (MRLA) MRLA sends a query representation of the current layer to all previous layers to retrieve query-related information from different levels of receptive fields. Our MRLA can improve 1.6% Top-1 accuracy on ResNet-50, while introducing only 0.16M parameters and 0.07B FLOPs.
  arXiv  Detail & Related papers  (2023-02-08T10:50:01Z)
• Occlusion-Aware Instance Segmentation via BiLayer Network Architectures [73.45922226843435]
  We propose Bilayer Convolutional Network (BCNet), where the top layer detects occluding objects (occluders) and the bottom layer infers partially occluded instances (occludees) We investigate the efficacy of bilayer structure using two popular convolutional network designs, namely, Fully Convolutional Network (FCN) and Graph Convolutional Network (GCN)
  arXiv  Detail & Related papers  (2022-08-08T21:39:26Z)
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks [58.868899595936476]
  This paper presents a new deep clustering approach termed image clustering with contrastive learning and multi-scale graph convolutional networks (IcicleGCN) Experiments on multiple image datasets demonstrate the superior clustering performance of IcicleGCN over the state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-14T19:16:56Z)
• Learning Target-aware Representation for Visual Tracking via Informative Interactions [49.552877881662475]
  We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer.
  arXiv  Detail & Related papers  (2022-01-07T16:22:27Z)
• CondenseNet V2: Sparse Feature Reactivation for Deep Networks [87.38447745642479]
  Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. We propose an alternative approach named sparse feature reactivation (SFR), aiming at actively increasing the utility of features for reusing. Our experiments show that the proposed models achieve promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO) in terms of both theoretical efficiency and practical speed.
  arXiv  Detail & Related papers  (2021-04-09T14:12:43Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars [2.7317088388886384]
  We present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We used ResNet based feature extractor, dilated convolutional layers in downsampling part, atrous convolutional layers in the upsampling part and used concat operation to merge them. A new attention module is proposed to encode more contextual information and enhance the receptive field of the network.
  arXiv  Detail & Related papers  (2020-06-30T20:19:09Z)
• CRNet: Cross-Reference Networks for Few-Shot Segmentation [59.85183776573642]
  Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images. Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-24T04:55:43Z)

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.