ppt课件-learningconvolutionalfeaturehierarchiesforvisual.pptVIP

Learning Convolutional Feature Hierarchies forVisual Recognition Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michael Mathieu, Yann LeCun NIPS 2010 Outline 1. Drawbacks in the Traditional Convolutional Methods 2. The Proposed Algorithm and Some Details 3. Experimental Results 4. Conslusions Convolutional Sparse Coding Solutions 1. Introducing Convolution Operator 2. Introducing Nonlinear Encoder Module Learning Convolutional Dictionaries 1. The Boundary Effects Due to Convolutions Learning an Efficient Encoder Patch Based vs Convolutional Sparse Modeling Multi-Stage Architecture Experiments 1: Object Recognition Using Caltech 101 Dataset Recognition Accuracy Pedestrian Detection(1) Pedestrian Detection(2) Conclusions 1. Convolutional training of feature extractors reduces the redundancy among filters compared with those obtained from patch based models. 2. Introduced two different convolutional encode functions for performing efficient feature extraction which is crucial for using sparse coding in real world applications. 3. The proposed sparse modeling systems has been applied through a successful multi-stage architecture on object recognition and pedestrian detection problems and performed comparably to similar systems. * Presented by Bo Chen Negative: 1. The representations of whole images are highly redundant because the training and the inference are performed at the patch level. 2. The inference for a whole image is computationally expensive. Apply a mask on the derivatives of the reconstruction error: where mask is a term-by-term multiplier that either puts zeros or gradually scales down the boundaries. 2. Computational Efficient Derivative 1. A New Smooth Shrinkage Operator: 2. To aid faster convergence, use stochastic diagonal Levenberg-Marquardt method to calculate a positive diagonal approximation to the hessian. The convolution operator enables the system to model local structures that appear anywhere in the signal