Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Convolutional neural nets (CNNs) have demonstrated remarkable performance in recent history. Such approaches tend to work in a "unidirectional" bottom-up feed-forward fashion. However, practical experience and biological evidence tells us that feedback plays a crucial role, particularly for detailed spatial understanding tasks. This work explores "bidirectional" architectures that also reason with top-down feedback: neural units are influenced by both lower and higher-level units. We do so by treating units as rectified latent variables in a quadratic energy function, which can be seen as a hierarchical Rectified Gaussian model (RGs) [39]. We show that RGs can be optimized with a quadratic program (QP), that can in turn be optimized with a recurrent neural network (with rectified linear units). This allows RGs to be trained with GPU-optimized gradient descent. From a theoretical perspective, RGs help establish a connection between CNNs and hierarchical probabilistic models. From a practical perspective, RGs are well suited for detailed spatial tasks that can benefit from top-down reasoning. We illustrate them on the challenging task of keypoint localization under occlusions, where local bottom-up evidence may be misleading. We demonstrate state-of-the-art results on challenging benchmarks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
Learning Deconvolution Network for Semantic Segmentation
Noh, H., Hong, S., & Han, B. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.178 · Cited by 4,422 · cited 1×
“2”
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
An Introduction to Variational Methods for Graphical Models
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999) · Machine Learning · doi:10.1023/a:1007665907178 · Cited by 3,791
A learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_7 · Cited by 3,402
Hierarchical Bayesian inference in the visual cortex
Lee, T. S., & Mumford, D. (2003) · Journal of the Optical Society of America A · doi:10.1364/josaa.20.001434 · Cited by 1,473 · cited 1×
“000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058”
Hochstein (2002) · doi:10.1016/s0896-6273(02)01091-7 · Cited by 1,397
Efficient object localization using Convolutional Networks
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., & Bregler, C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298664 · Cited by 1,365
Hinton, G. E., Krizhevsky, A., & Wang, S. D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_6 · Cited by 1,360 · cited 1×
“Neuron, 22 (3):593–604, 1999.”
The neurophysiology of figure-ground segregation in primary visual cortex
Lamme, V. (1995) · The Journal of Neuroscience · doi:10.1523/jneurosci.15-02-01605.1995 · Cited by 946
Contextual modulation in primary visual cortex
Zipser, K., Lamme, V. A. F., & Schiller, P. H. (1996) · The Journal of Neuroscience · doi:10.1523/jneurosci.16-22-07376.1996 · Cited by 873
Human Pose Estimation with Iterative Error Feedback
Carreira, J., Agrawal, P., Fragkiadaki, K., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.512 · Cited by 805
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · arXiv · doi:10.48550/arxiv.1403.6382 · Cited by 607
Learning task-dependent distributed representations by backpropagation through structure
Goller, C., & Kuchler, A. (2002) · Proceedings of International Conference on Neural Networks (ICNN'96) · doi:10.1109/icnn.1996.548916 · Cited by 581
Attention Modulates Contextual Influences in the Primary Visual Cortex of Alert Monkeys
Ito, M., & Gilbert, C. D. (1999) · Neuron · doi:10.1016/s0896-6273(00)80713-8 · Cited by 456 · cited 1×
“However, vision with scrutiny tasks appear to require top-down feedback processing [8, 10], which is missing in the “uni-directional” CNNs.”
Background
Cited by
Deep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984
“The high-to-low process aims to generate low-resolution and high-level representations, and the low-to-high process aims to produce highresolution representations [4, 11, 22, 70, 39, 60].”
BackgroundStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634
“Hu and Ramanan [27] have an architecture more similar to ours that can also be used for multiple stages of predictions, but their model ties weights in the bottom-up and top-down portions of computation as well as across iterations.”
BackgroundMonocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., & Theobalt, C. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00064 · Cited by 1,142
VNect: real-time 3D human pose estimation with a single RGB camera
Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Seidel, H.-P., Xu, W., Casas, D., & Theobalt, C. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073596 · Cited by 1,113
Multi-context Attention for Human Pose Estimation
Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A. L., & Wang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.601 · Cited by 737
Metadata
- Authors
- Hu, P., & Ramanan, D.
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 5600-5609
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963484342
- Cited by
- 94
- References
- 17
- FWCI
- 6.11
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.