Learning to Learn Parameterized Classification Networks for Scalable Input Images

• URL: http://arxiv.org/abs/2007.06181v1
• Date: Mon, 13 Jul 2020 04:27:25 GMT
• Title: Learning to Learn Parameterized Classification Networks for Scalable Input Images
• Authors: Duo Li, Anbang Yao and Qifeng Chen
• Abstract summary: Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
• Score: 76.44375136492827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To achieve efficient and flexible image classification at runtime, we employ meta learners to generate convolutional weights of main networks for various input scales and maintain privatized Batch Normalization layers per scale. For improved training performance, we further utilize knowledge distillation on the fly over model predictions based on different input resolutions. The learned meta network could dynamically parameterize main networks to act on input images of arbitrary size with consistently better accuracy compared to individually trained models. Extensive experiments on the ImageNet demonstrate that our method achieves an improved accuracy-efficiency trade-off during the adaptive inference process. By switching executable input resolutions, our method could satisfy the requirement of fast adaption in different resource-constrained environments. Code and models are available at https://github.com/d-li14/SAN.

Related papers

• 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)
• Neural Data-Dependent Transform for Learned Image Compression [72.86505042102155]
  We build a neural data-dependent transform and introduce a continuous online mode decision mechanism to jointly optimize the coding efficiency for each individual image. The experimental results show the effectiveness of the proposed neural-syntax design and the continuous online mode decision mechanism.
  arXiv  Detail & Related papers  (2022-03-09T14:56:48Z)
• Correlation between image quality metrics of magnetic resonance images and the neural network segmentation accuracy [0.0]
  In this study, we investigated the correlation between the image quality metrics of MR images with the neural network segmentation accuracy. The difference in the segmentation accuracy between models based on the random training inputs with IQM based training inputs shed light on the role of image quality metrics on segmentation accuracy.
  arXiv  Detail & Related papers  (2021-11-01T17:02:34Z)
• Differentiable Patch Selection for Image Recognition [37.11810982945019]
  We propose a differentiable Top-K operator to select the most relevant parts of the input to process high resolution images. We show results for traffic sign recognition, inter-patch relationship reasoning, and fine-grained recognition without using object/part bounding box annotations.
  arXiv  Detail & Related papers  (2021-04-07T11:15:51Z)
• Retrieval Augmentation to Improve Robustness and Interpretability of Deep Neural Networks [3.0410237490041805]
  In this work, we actively exploit the training data to improve the robustness and interpretability of deep neural networks. Specifically, the proposed approach uses the target of the nearest input example to initialize the memory state of an LSTM model or to guide attention mechanisms. Results show the effectiveness of the proposed models for the two tasks, on the widely used Flickr8 and IMDB datasets.
  arXiv  Detail & Related papers  (2021-02-25T17:38:31Z)
• Encoding Robustness to Image Style via Adversarial Feature Perturbations [72.81911076841408]
  We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce robust models. Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training.
  arXiv  Detail & Related papers  (2020-09-18T17:52:34Z)
• Resolution Switchable Networks for Runtime Efficient Image Recognition [46.09537029831355]
  We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Networks trained with the proposed method are named Resolution Switchable Networks (RS-Nets)
  arXiv  Detail & Related papers  (2020-07-19T02:12:59Z)
• ResNeSt: Split-Attention Networks [86.25490825631763]
  We present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification.
  arXiv  Detail & Related papers  (2020-04-19T20:40:31Z)

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.