Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales

• URL: http://arxiv.org/abs/2106.06418v1
• Date: Fri, 11 Jun 2021 14:22:26 GMT
• Title: Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
• Authors: Ylva Jansson and Tony Lindeberg
• Abstract summary: We show that two previously proposed scale channel network designs do not generalise well to scales not present in the training set. We propose a new type of foveated scale channel architecture, where the scale channels process increasingly larger parts of the image with decreasing resolution. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single scale training data, and do also give improved performance when learning from transformations with large scale variations in the small sample regime.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invariance can then, in principle, be achieved by using weight sharing between the scale channels together with max or average pooling over the outputs from the scale channels. The ability of such scale channel networks to generalise to scales not present in the training set over significant scale ranges has, however, not previously been explored. In this paper, we present a systematic study of this methodology by implementing different types of scale channel networks and evaluating their ability to generalise to previously unseen scales. We develop a formalism for analysing the covariance and invariance properties of scale channel networks, and explore how different design choices, unique to scaling transformations, affect the overall performance of scale channel networks. We first show that two previously proposed scale channel network designs do not generalise well to scales not present in the training set. We explain theoretically and demonstrate experimentally why generalisation fails in these cases. We then propose a new type of foveated scale channel architecture}, where the scale channels process increasingly larger parts of the image with decreasing resolution. This new type of scale channel network is shown to generalise extremely well, provided sufficient image resolution and the absence of boundary effects. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single scale training data, and do also give improved performance when learning from datasets with large scale variations in the small sample regime.

Related papers

• Feature-Learning Networks Are Consistent Across Widths At Realistic Scales [72.27228085606147]
  We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also agree in their point-wise test predictions throughout training. We observe, however, that ensembles of narrower networks perform worse than a single wide network.
  arXiv  Detail & Related papers  (2023-05-28T17:09:32Z)
• Riesz networks: scale invariant neural networks in a single forward pass [0.7673339435080445]
  We introduce the Riesz network, a novel scale invariant neural network. As an application example, we consider detecting and segmenting cracks in tomographic images of concrete. We then validate its performance in segmenting simulated and real tomographic images featuring a wide range of crack widths.
  arXiv  Detail & Related papers  (2023-05-08T12:39:49Z)
• 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)
• Group Fisher Pruning for Practical Network Compression [58.25776612812883]
  We present a general channel pruning approach that can be applied to various complicated structures. We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Our method can be used to prune any structures including those with coupled channels.
  arXiv  Detail & Related papers  (2021-08-02T08:21:44Z)
• Channel Scaling: A Scale-and-Select Approach for Transfer Learning [2.6304695993930594]
  Transfer learning with pre-trained neural networks is a common strategy for training classifiers in medical image analysis. We propose a novel approach to efficiently build small and well performing networks by introducing the channel-scaling layers. By imposing L1 regularization and thresholding on the scaling weights, this framework iteratively removes unnecessary feature channels from a pre-trained model.
  arXiv  Detail & Related papers  (2021-03-22T23:26:57Z)
• Scale-covariant and scale-invariant Gaussian derivative networks [0.0]
  This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.
  arXiv  Detail & Related papers  (2020-11-30T13:15:10Z)
• On Robustness and Transferability of Convolutional Neural Networks [147.71743081671508]
  Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. We study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time. We find that increasing both the training set and model sizes significantly improve the distributional shift robustness.
  arXiv  Detail & Related papers  (2020-07-16T18:39:04Z)
• On the Predictability of Pruning Across Scales [29.94870276983399]
  We show that the error of magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. As neural networks become ever larger and costlier to train, our findings suggest a framework for reasoning conceptually and analytically about a standard method for unstructured pruning.
  arXiv  Detail & Related papers  (2020-06-18T15:41:46Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges [0.0]
  A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. We propose a new type of foveated scale channel architecture, where the scale channels process increasingly larger parts of the image with decreasing resolution. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single scale training data, and do also give improvements in the small sample regime.
  arXiv  Detail & Related papers  (2020-04-03T13:00:35Z)
• Crowd Counting via Hierarchical Scale Recalibration Network [61.09833400167511]
  We propose a novel Hierarchical Scale Recalibration Network (HSRNet) to tackle the task of crowd counting. HSRNet models rich contextual dependencies and recalibrating multiple scale-associated information. Our approach can ignore various noises selectively and focus on appropriate crowd scales automatically.
  arXiv  Detail & Related papers  (2020-03-07T10:06:47Z)

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.