Toward a Deeper Understanding: RetNet Viewed through Convolution

• URL: http://arxiv.org/abs/2309.05375v2
• Date: Sun, 29 Oct 2023 07:08:04 GMT
• Title: Toward a Deeper Understanding: RetNet Viewed through Convolution
• Authors: Chenghao Li, Chaoning Zhang
• Abstract summary: Vision Transformer (ViT) can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources. This paper investigates the effectiveness of RetNet from a CNN perspective and presents a variant of RetNet tailored to the visual domain. We propose a novel Gaussian mixture mask (GMM) in which one mask only has two learnable parameters and it can be conveniently used in any ViT variants whose attention mechanism allows the use of masks.
• Score: 25.8904146140577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources. Recently, the outstanding performance of RetNet in the field of language modeling has garnered attention, surpassing that of the Transformer with explicit local modeling, shifting researchers' focus towards Transformers in the CV field. This paper investigates the effectiveness of RetNet from a CNN perspective and presents a variant of RetNet tailored to the visual domain. Similar to RetNet we improves ViT's local modeling by applying a weight mask on the original self-attention matrix. A straightforward way to locally adapt the self-attention matrix can be realized by an element-wise learnable weight mask (ELM), for which our preliminary results show promising results. However, the element-wise simple learnable weight mask not only induces a non-trivial additional parameter overhead but also increases the optimization complexity. To this end, this work proposes a novel Gaussian mixture mask (GMM) in which one mask only has two learnable parameters and it can be conveniently used in any ViT variants whose attention mechanism allows the use of masks. Experimental results on multiple small datasets demonstrate that the effectiveness of our proposed Gaussian mask for boosting ViTs for free (almost zero additional parameter or computation cost). Our code can be publicly available at https://github.com/CatworldLee/Gaussian-Mixture-Mask-Attention.

Related papers

• Triple Point Masking [49.39218611030084]
  Existing 3D mask learning methods encounter performance bottlenecks under limited data. We introduce a triple point masking scheme, named TPM, which serves as a scalable framework for pre-training of masked autoencoders. Extensive experiments show that the four baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks.
  arXiv  Detail & Related papers  (2024-09-26T05:33:30Z)
• Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
  Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
  arXiv  Detail & Related papers  (2024-07-08T12:28:56Z)
• Masked autoencoders are effective solution to transformer data-hungry [0.0]
  Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. ViT lacks the inductive bias inherent to convolution making it require a large amount of data for training. Masked autoencoders (MAE) can make the transformer focus more on the image itself.
  arXiv  Detail & Related papers  (2022-12-12T03:15:19Z)
• Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation [0.0]
  This work proposes a new WSSS method dubbed ViT-PCM (ViT Patch-Class Mapping), not based on CAM. Our model outperforms the state-of-the-art on baseline pseudo-masks (BPM), where we achieve $69.3%$ mIoU on PascalVOC 2012 $val$ set.
  arXiv  Detail & Related papers  (2022-10-31T15:32:23Z)
• MaskViT: Masked Visual Pre-Training for Video Prediction [29.25521342538311]
  We create good video prediction models by pre-training transformers via masked visual modeling. MaskViT outperforms prior works in video prediction, is parameter efficient and can generate high-resolution videos. Our work suggests that we can endow embodied agents with powerful predictive models by leveraging the general framework of masked visual modeling.
  arXiv  Detail & Related papers  (2022-06-23T17:59:33Z)
• HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling [126.89573619301953]
  We propose a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) HiViT enjoys both high efficiency and good performance in MIM. In running MAE on ImageNet-1K, HiViT-B reports a +0.6% accuracy gain over ViT-B and a 1.9$times$ speed-up over Swin-B.
  arXiv  Detail & Related papers  (2022-05-30T09:34:44Z)
• Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection [39.37861288287621]
  A MIM pre-trained vanilla ViT can work surprisingly well in the challenging object-level recognition scenario. A random compact convolutional stem supplants the pre-trained large kernel patchify stem. The proposed detector, named MIMDet, enables a MIM pre-trained vanilla ViT to outperform hierarchical Swin Transformer by 2.3 box AP and 2.5 mask AP on.
  arXiv  Detail & Related papers  (2022-04-06T17:59:04Z)
• Pruning Self-attentions into Convolutional Layers in Single Path [89.55361659622305]
  Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. We propose Single-Path Vision Transformer pruning (SPViT) to efficiently and automatically compress the pre-trained ViTs. Our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.
  arXiv  Detail & Related papers  (2021-11-23T11:35:54Z)
• Container: Context Aggregation Network [83.12004501984043]
  Recent finding shows that a simple based solution without any traditional convolutional or Transformer components can produce effective visual representations. We present the model (CONText Ion NERtwok), a general-purpose building block for multi-head context aggregation. In contrast to Transformer-based methods that do not scale well to downstream tasks that rely on larger input image resolutions, our efficient network, named modellight, can be employed in object detection and instance segmentation networks.
  arXiv  Detail & Related papers  (2021-06-02T18:09:11Z)
• PointINS: Point-based Instance Segmentation [117.38579097923052]
  Mask representation in instance segmentation with Point-of-Interest (PoI) features is challenging because learning a high-dimensional mask feature for each instance requires a heavy computing burden. We propose an instance-aware convolution, which decomposes this mask representation learning task into two tractable modules. Along with instance-aware convolution, we propose PointINS, a simple and practical instance segmentation approach.
  arXiv  Detail & Related papers  (2020-03-13T08:24:58Z)

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.