Analyzing the Performance of Multilayer Neural Networks for Object Recognition
arXiv:1407.1610
Abstract
In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.
Published in European Conference on Computer Vision 2014 (ECCV-2014)
Cited by in corpus (17)
- What makes ImageNet good for transfer learning?
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- The Devil is in the Tails: Fine-grained Classification in the Wild
- PixelNet: Representation of the pixels, by the pixels, and for the pixels
- Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
- Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
- Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes
- Factors of Transferability for a Generic ConvNet Representation
- Object Detection Free Instance Segmentation With Labeling Transformations
- Visual Discovery at Pinterest
- All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
- The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification
- Learning Sparse, Distributed Representations using the Hebbian Principle
- Kill Two Birds With One Stone: Boosting Both Object Detection Accuracy and Speed With adaptive Patch-of-Interest Composition
- Manifestation of Image Contrast in Deep Networks
- On the Exploration of Convolutional Fusion Networks for Visual Recognition