Efficient object localization using Convolutional Networks

By Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, C. Bregler. 2014

1,451 citations recorded by the source corpus.

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model [21] to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC [20] dataset and outperforms all existing approaches on the MPII-human-pose dataset [1].

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

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields (2016, background): “These top-down approaches directly leverage existing techniques for single-person pose estimation [17, 31, 18, 28, 29, 7, 30, 5, 6, 20], but suffer from early commitment: if the person detector fails–as it is prone to do when people are in close proximity–there is no recourse to recovery.”
Recent advances in convolutional neural networks (2015, methodology): “[51] propose a CNN architecture which includes a position refinement model after a rough pose estimation CNN.”
Learning Sparse Neural Networks through L0 Regularization (2017, background): “Notice that in the interpretation we adopt the gate is shared across all locations of the feature map for convolutional layers, akin to spatial dropout (Tompson et al., 2015).”
DropBlock: A regularization method for convolutional networks (2018, methodology): “DropBlock resembles dropout [1] when block_size = 1 and resembles SpatialDropout [20] when block_size covers the full feature map.”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, background): “The problem of human pose estimation has been intensively studied in the last years, from Pictorial Structures [2, 17, 37] to more recent CNN approaches [34, 25, 38, 20, 41, 54, 5, 51, 52, 36].”
Convolutional Two-Stream Network Fusion for Video Action Recognition (2016, background): “However, action recognition has not yet seen the substantial gains in performance that have been achieved in other areas by ConvNets, e.g. image classiﬁcation [12, 23, 27], human face recognition [21], and human pose estimation [29].”
Training CNNs with Low-Rank Filters for Efficient Image Classification (2015, methodology): “Convolutional neural networks (CNNs) have been used increasingly succesfully to solve challenging computer vision problems such as image classification (Krizhevsky et al., 2012), object detection (Ren et al., 2015), and human pose estimation (Tompson et al., 2015).”
Human Pose Estimation with Iterative Error Feedback (2015, methodology): “Note however that the emphasis in Tompson et al’s system was efficiency and they trained and tested their model using original image scales – searching over a multiscale image pyramid or using our automatic rescaling procedure should presumably improve their performance.”
Single Image 3D Interpreter Network (2016, methodology): “On this dataset, we employ a fine-level network for post-processing, as suggested by [32].”
Temporal Convolutional Networks for Action Segmentation and Detection (2016, background): “Using dropout on full convolutional filters [32], as opposed to individual weights, improves performance and produces smoother looking weights.”
Flowing ConvNets for Human Pose Estimation in Videos (2015, methodology): “Predictions are provided by the authors of [5, 35] and evaluation code by the authors of [35].”