# Efficient Object Localization Using Convolutional Networks

arXiv: https://arxiv.org/abs/1411.4280 · HTML: https://mlsanity.com/paper/1411.4280/

## Key facts

- Cited by 227 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2014.

## Built on by (most cited first, 30 of 227)

- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Pure Transformers are Powerful Graph Learners](https://mlsanity.com/paper/2207.02505/) (2022)
- [Masked World Models for Visual Control](https://mlsanity.com/paper/2206.14244/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [What to Hide from Your Students: Attention-Guided Masked Image Modeling](https://mlsanity.com/paper/2203.12719/) (2022)
- [Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2111.14213/) (2021)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [TransFER: Learning Relation-aware Facial Expression Representations with Transformers](https://mlsanity.com/paper/2108.11116/) (2021)
- [MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation](https://mlsanity.com/paper/2103.12605/) (2021)
- [When Do We Not Need Larger Vision Models?](https://mlsanity.com/paper/2403.13043/) (2024)
- [Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers](https://mlsanity.com/paper/2303.01610/) (2023)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [ReFit: Recurrent Fitting Network for 3D Human Recovery](https://mlsanity.com/paper/2308.11184/) (2023)
- [A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark](https://mlsanity.com/paper/2203.00131/) (2022)
- [Reflash Dropout in Image Super-Resolution](https://mlsanity.com/paper/2112.12089/) (2021)
- [A Modern Self-Referential Weight Matrix That Learns to Modify Itself](https://mlsanity.com/paper/2202.05780/) (2022)
- [DualNet: Continual Learning, Fast and Slow](https://mlsanity.com/paper/2110.00175/) (2021)
- [AutoDropout: Learning Dropout Patterns to Regularize Deep Networks](https://mlsanity.com/paper/2101.01761/) (2021)
- [LoRA Dropout as a Sparsity Regularizer for Overfitting Control](https://mlsanity.com/paper/2404.09610/) (2024)
- [Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words](https://mlsanity.com/paper/2309.16108/) (2023)
- [Emergence of Maps in the Memories of Blind Navigation Agents](https://mlsanity.com/paper/2301.13261/) (2023)
- [Uncertainty guided semi-supervised segmentation of retinal layers in OCT images](https://mlsanity.com/paper/2103.02083/) (2021)
- [OCELOT: Overlapped Cell on Tissue Dataset for Histopathology](https://mlsanity.com/paper/2303.13110/) (2023)
- [Contextual Dropout: An Efficient Sample-Dependent Dropout Module](https://mlsanity.com/paper/2103.04181/) (2021)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Towards Improving Calibration in Object Detection Under Domain Shift](https://mlsanity.com/paper/2209.07601/) (2022)
- [Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2110.00249/) (2021)
- [Network Augmentation for Tiny Deep Learning](https://mlsanity.com/paper/2110.08890/) (2021)

## Abstract (arXiv)

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 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 dataset and outperforms all existing approaches on the MPII-human-pose dataset.