Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection

Abstract

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building block alternative to the common convolution-MP cascade of DCNNs; while having identical complexity to MP, Epitomic Convolution allows for parameter sharing across different filters, resulting in faster convergence and better generalization. Second, we introduce a Multiple Instance Learning approach to explicitly accommodate global translation and scaling when training a DCNN exclusively with class labels. For this we rely on a `patchwork' data structure that efficiently lays out all image scales and positions as candidates to a DCNN. Factoring global and local deformations allows a DCNN to `focus its resources' on the treatment of non-rigid deformations and yields a substantial classification accuracy improvement. Third, further pursuing this idea, we develop an efficient DCNN sliding window object detector that employs explicit search over position, scale, and aspect ratio. We provide competitive image classification and localization results on the ImageNet dataset and object detection results on the Pascal VOC 2007 benchmark.

13 pages, 7 figures, 5 tables. arXiv admin note: substantial text overlap with arXiv:1406.2732

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Going Deeper with Convolutions
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
• Deformable Part Models are Convolutional Neural Networks
• Deep Epitomic Convolutional Neural Networks

Cited by in corpus (11)

• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Particular object retrieval with integral max-pooling of CNN activations
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Deep Learning for Semantic Part Segmentation with High-Level Guidance
• Multi-level Contextual RNNs with Attention Model for Scene Labeling
• Signs in time: Encoding human motion as a temporal image
• A multi-stage GAN for multi-organ chest X-ray image generation and segmentation
• CNN based texture synthesize with Semantic segment
• Convolutional Channel Features
• MoE-SPNet: A Mixture-of-Experts Scene Parsing Network