Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures

• URL: http://arxiv.org/abs/2402.12418v1
• Date: Mon, 19 Feb 2024 09:52:45 GMT
• Title: Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures
• Authors: Akash Guna R.T, Arnav Chavan, Deepak Gupta
• Abstract summary: We introduce an automated scaling approach leveraging second-order loss landscape information. Our method is flexible towards skip connections a mainstay in modern vision transformers. We introduce the first intact scaling mechanism for vision transformers, a step towards efficient model scaling.
• Score: 9.91972450276408
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach leveraging second-order loss landscape information. Our method is flexible towards skip connections a mainstay in modern vision transformers. Our training-aware method jointly scales and trains transformers without additional training iterations. Motivated by the hypothesis that not all neurons need uniform depth complexity, our approach embraces depth heterogeneity. Extensive evaluations on DeiT-S with ImageNet100 show a 2.5% accuracy gain and 10% parameter efficiency improvement over conventional scaling. Scaled networks demonstrate superior performance upon training small scale datasets from scratch. We introduce the first intact scaling mechanism for vision transformers, a step towards efficient model scaling.

Related papers

• Scale Propagation Network for Generalizable Depth Completion [16.733495588009184]
  We propose a novel scale propagation normalization (SP-Norm) method to propagate scales from input to output. We also develop a new network architecture based on SP-Norm and the ConvNeXt V2 backbone. Our model consistently achieves the best accuracy with faster speed and lower memory when compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-24T03:53:06Z)
• Super Consistency of Neural Network Landscapes and Learning Rate Transfer [72.54450821671624]
  We study the landscape through the lens of the loss Hessian. We find that certain spectral properties under $mu$P are largely independent of the size of the network. We show that in the Neural Tangent Kernel (NTK) and other scaling regimes, the sharpness exhibits very different dynamics at different scales.
  arXiv  Detail & Related papers  (2024-02-27T12:28:01Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• Meta-Principled Family of Hyperparameter Scaling Strategies [9.89901717499058]
  We calculate the scalings of dynamical observables -- network outputs, neural tangent kernels, and differentials of neural tangent kernels -- for wide and deep neural networks. We observe that various infinite-width limits examined in the literature correspond to the distinct corners of the interconnected web.
  arXiv  Detail & Related papers  (2022-10-10T18:00:01Z)
• Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation [69.45176408639483]
  We reform the conv layer by resorting to the scale-space theory. We build a novel style named SCale AttentioN Conv Neural Network (textbfSCAN-CNN) As a single-shot scheme, the inference is more efficient than multi-shot fusion.
  arXiv  Detail & Related papers  (2022-09-19T06:35:04Z)
• FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks [77.34726150561087]
  We show how to explore high-dimensional landscape characteristics of neural networks. We generalize observations on small neural networks to more complex systems. An interactive dashboard opens up a number of possible application networks.
  arXiv  Detail & Related papers  (2022-04-09T16:41:53Z)
• ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers [31.908276711898548]
  Methods for data-efficient recognition from body poses increasingly leverage skeleton sequences structured as image-like arrays. We look at this paradigm from the perspective of transformer networks, for the first time exploring visual transformers as data-efficient encoders of skeleton movement. In our pipeline, body pose sequences cast as image-like representations are converted into patch embeddings and then passed to a visual transformer backbone optimized with deep metric learning.
  arXiv  Detail & Related papers  (2022-02-23T11:11:54Z)
• Exploiting Invariance in Training Deep Neural Networks [4.169130102668252]
  Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. Tested on ImageNet, MS COCO, and Cityscapes datasets, our proposed technique requires fewer iterations to train, surpasses all baselines by a large margin, seamlessly works on both small and large batch size training, and applies to different computer vision tasks of image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2021-03-30T19:18:31Z)
• Vision Transformers for Dense Prediction [77.34726150561087]
  We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. Our experiments show that this architecture yields substantial improvements on dense prediction tasks.
  arXiv  Detail & Related papers  (2021-03-24T18:01:17Z)
• Transformers Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)

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.