Top-Down Learning for Structured Labeling with Convolutional Pseudoprior

By Saining Xie, Xun Huang, Zhuowen Tu. 2015

39 citations recorded by the source corpus.

Current practice in convolutional neural networks (CNN) remains largely bottom-up and the role of top-down process in CNN for pattern analysis and visual inference is not very clear. In this paper, we propose a new method for structured labeling by developing convolutional pseudo-prior (ConvPP) on the ground-truth labels. Our method has several interesting properties: (1) compared with classical machine learning algorithms like CRFs and Structural SVM, ConvPP automatically learns rich convolutional kernels to capture both short- and long- range contexts; (2) compared with cascade classifiers like Auto-Context, ConvPP avoids the iterative steps of learning a series of discriminative classifiers and automatically learns contextual configurations; (3) compared with recent efforts combing CNN models with CRFs and RNNs, ConvPP learns convolution in the labeling space with much improved modeling capability and less manual specification; (4) compared with Bayesian models like MRFs, ConvPP capitalizes on the rich representation power of convolution by automatically learning priors built on convolutional filters. We accomplish our task using pseudo-likelihood approximation to the prior under a novel fixed-point network structure that facilitates an end-to-end learning process. We show state-of-the-art results on sequential labeling and image labeling benchmarks.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Image-to-Image Translation with Conditional Adversarial Networks (2016, methodology): “A large body of literature has considered losses of this kind, with methods including conditional random fields [9], the SSIM metric [53], feature matching [13], nonparametric losses [34], the convolutional pseudo-prior [54], and losses based on matching covariance statistics [27].”
On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation (2018, background): “The contributions in this direction include Conditional Random Fields (CRFs) and its variants (which remain a popular choice) [24, 7, 49], CRFs as Recurrent Neural Networks [49], iterative inference denoising autoencoders [37], convolutional pseudo-priors [45], as well as graph-cuts, watersheds and ”
Iterative Visual Reasoning Beyond Convolutions (2018, background): “Even the most recent developments such as top-down module [50, 29, 43], pairwise module [40], iterative feedback [48, 34, 2], attention [53], and memory [51, 4] are motivated to leverage such power and depend on variants of convolutions for reasoning.”
Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling (2017, unknown): “ConvPP-8 [63] - 41.”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “The ﬁrst type of model incorporates image or scene level context [5, 36, Figure 1: Evidence of image-level context reasoning inside ConvNets.”
Dense Recurrent Neural Networks for Scene Labeling (2018, unknown): “85.9 53.9 41.2 Liu et al [30] 76.7 n/a n/a ParseNet [31] 86.8 52.0 40.4 ClassRare [49] 79.8 48.7 n/a Tighe et al [44] 75.6 41.1 n/a CNN-CRF [29] 88.1 53.4 44.9 DilatedNet [50] 86.8 n/a 41.5 ConvPP-8s [47] n/a n/a 40.7 CNN-LSTM [6] 70.1 22.6 n/a Farabet et al [15] 72.3 50.8 n/a Sharma et al [40] 75.5”