RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network

• URL: http://arxiv.org/abs/2206.14098v2
• Date: Fri, 28 Apr 2023 23:54:40 GMT
• Title: RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
• Authors: Vitaliy Chiley, Vithursan Thangarasa, Abhay Gupta, Anshul Samar, Joel Hestness, Dennis DeCoste
• Abstract summary: RevSilo is the first reversible multi-scale feature fusion module. We create RevBiFPN, a fully reversible bidirectional feature pyramid network. RevBiFPN provides up to a 2.5% boost in AP over HRNet using fewer MACs and a 2.4x reduction in training-time memory.
• Score: 3.54359747576165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work introduces RevSilo, the first reversible bidirectional multi-scale feature fusion module. Like other reversible methods, RevSilo eliminates the need to store hidden activations by recomputing them. However, existing reversible methods do not apply to multi-scale feature fusion and are, therefore, not applicable to a large class of networks. Bidirectional multi-scale feature fusion promotes local and global coherence and has become a de facto design principle for networks targeting spatially sensitive tasks, e.g., HRNet (Sun et al., 2019a) and EfficientDet (Tan et al., 2020). These networks achieve state-of-the-art results across various computer vision tasks when paired with high-resolution inputs. However, training them requires substantial accelerator memory for saving large, multi-resolution activations. These memory requirements inherently cap the size of neural networks, limiting improvements that come from scale. Operating across resolution scales, RevSilo alleviates these issues. Stacking RevSilos, we create RevBiFPN, a fully reversible bidirectional feature pyramid network. RevBiFPN is competitive with networks such as EfficientNet while using up to 19.8x lesser training memory for image classification. When fine-tuned on MS COCO, RevBiFPN provides up to a 2.5% boost in AP over HRNet using fewer MACs and a 2.4x reduction in training-time memory.

Related papers

• Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors [4.95475852994362]
  We propose a new form of quantization to tile neural network layers with sequences of bits to achieve sub-bit compression of binary-weighted neural networks. We employ the approach to both fully-connected and convolutional layers, which make up the breadth of space in most neural architectures.
  arXiv  Detail & Related papers  (2024-07-16T15:55:38Z)
• FBPT: A Fully Binary Point Transformer [12.373066597900127]
  This paper presents a novel Fully Binary Point Cloud Transformer (FBPT) model which has the potential to be widely applied and expanded in the fields of robotics and mobile devices. By compressing the weights and activations of a 32-bit full-precision network to 1-bit binary values, the proposed binary point cloud Transformer network significantly reduces the storage footprint and computational resource requirements. The primary focus of this paper is on addressing the performance degradation issue caused by the use of binary point cloud Transformer modules.
  arXiv  Detail & Related papers  (2024-03-15T03:45:10Z)
• LR-CNN: Lightweight Row-centric Convolutional Neural Network Training for Memory Reduction [21.388549904063538]
  Convolutional Neural Network with a multi-layer architecture has advanced rapidly. Current efforts mitigate such bottleneck by external auxiliary solutions with additional hardware costs, and internal modifications with potential accuracy penalty. We break the traditional layer-by-layer (column) dataflow rule. Now operations are novelly re-organized into rows throughout all convolution layers. This lightweight design allows a majority of intermediate data to be removed without any loss of accuracy.
  arXiv  Detail & Related papers  (2024-01-21T12:19:13Z)
• Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning [81.0108753452546]
  We propose Dynamic Reversible Dual-Residual Networks, or Dr$2$Net, to finetune a pretrained model with substantially reduced memory consumption. Dr$2$Net contains two types of residual connections, one maintaining the residual structure in the pretrained models, and the other making the network reversible. We show that Dr$2$Net can reach comparable performance to conventional finetuning but with significantly less memory usage.
  arXiv  Detail & Related papers  (2024-01-08T18:59:31Z)
• BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance [54.214426436283134]
  Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. We present a strong yet efficient binary neural network for KWS, namely BiFSMNv2, pushing it to the real-network accuracy performance. We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1x speedup and 20.2x storage-saving on edge hardware.
  arXiv  Detail & Related papers  (2022-11-13T18:31:45Z)
• BiFSMN: Binary Neural Network for Keyword Spotting [47.46397208920726]
  BiFSMN is an accurate and extreme-efficient binary neural network for KWS. We show that BiFSMN can achieve an impressive 22.3x speedup and 15.5x storage-saving on real-world edge hardware.
  arXiv  Detail & Related papers  (2022-02-14T05:16:53Z)
• 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)
• 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)
• Invertible Residual Network with Regularization for Effective Medical Image Segmentation [2.76240219662896]
  Invertible neural networks have been applied to significantly reduce activation memory footprint when training neural networks with backpropagation. We propose two versions of the invertible Residual Network, namely Partially Invertible Residual Network (Partially-InvRes) and Fully Invertible Residual Network (Fully-InvRes) Our results indicate that by using partially/fully invertible networks as the central workhorse in volumetric segmentation, we not only reduce memory overhead but also achieve compatible segmentation performance compared against the non-invertible 3D Unet.
  arXiv  Detail & Related papers  (2021-03-16T13:19:59Z)
• MicroNet: Towards Image Recognition with Extremely Low FLOPs [117.96848315180407]
  MicroNet is an efficient convolutional neural network using extremely low computational cost. A family of MicroNets achieve a significant performance gain over the state-of-the-art in the low FLOP regime. For instance, MicroNet-M1 achieves 61.1% top-1 accuracy on ImageNet classification with 12 MFLOPs, outperforming MobileNetV3 by 11.3%.
  arXiv  Detail & Related papers  (2020-11-24T18:59:39Z)
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [76.05981545084738]
  We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts. We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-03-07T02:12:02Z)

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.