EGL++: Extending Expected Gradient Length to Active Learning for Human Pose Estimation

• URL: http://arxiv.org/abs/2104.09493v1
• Date: Mon, 19 Apr 2021 17:56:59 GMT
• Title: EGL++: Extending Expected Gradient Length to Active Learning for Human Pose Estimation
• Authors: Megh Shukla
• Abstract summary: State of the art human pose estimation models rely on large quantities of labelled data for robust performance. EGL++ is a novel algorithm that extends expected gradient length to tasks where discrete labels are not available.
• Score: 2.0305676256390934
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: State of the art human pose estimation models continue to rely on large quantities of labelled data for robust performance. Since labelling budget is often constrained, active learning algorithms are important in retaining the overall performance of the model at a lower cost. Although active learning has been well studied in literature, few techniques are reported for human pose estimation. In this paper, we theoretically derive expected gradient length for regression, and propose EGL++, a novel heuristic algorithm that extends expected gradient length to tasks where discrete labels are not available. We achieve this by computing low dimensional representations of the original images which are then used to form a neighborhood graph. We use this graph to: 1) Obtain a set of neighbors for a given sample, with each neighbor iteratively assumed to represent the ground truth for gradient calculation 2) Quantify the probability of each sample being a neighbor in the above set, facilitating the expected gradient step. Such an approach allows us to provide an approximate solution to the otherwise intractable task of integrating over the continuous output domain. To validate EGL++, we use the same datasets (Leeds Sports Pose, MPII) and experimental design as suggested by previous literature, achieving competitive results in comparison to these methods.

Related papers

• LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training [2.762397703396293]
  Loss Prediction Loss with Gradient Norm (LPLgrad) is designed to quantify model uncertainty effectively and improve the accuracy of image classification tasks. LPLgrad operates in two distinct phases: (i) em Training Phase aims to predict the loss for input features by jointly training a main model and an auxiliary model. This dual-model approach enhances the ability to extract complex input features and learn intrinsic patterns from the data effectively.
  arXiv  Detail & Related papers  (2024-11-20T18:12:59Z)
• Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding [15.834419910916933]
  We propose a novel positional encoding technique, PerturbPE, that extracts consistent and regular components from the eigenbasis. Our results support our theoretical findings, e.g. our experimental analysis observed a performance enhancement of up to $12%$ on the Human3.6M dataset. Our novel approach significantly enhances performance in scenarios where two edges are missing, setting a new benchmark for state-of-the-art.
  arXiv  Detail & Related papers  (2024-05-27T17:48:54Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Learning Large Graph Property Prediction via Graph Segment Training [61.344814074335304]
  We propose a general framework that allows learning large graph property prediction with a constant memory footprint. We refine the GST paradigm by introducing a historical embedding table to efficiently obtain embeddings for segments not sampled for backpropagation. Our experiments show that GST-EFD is both memory-efficient and fast, while offering a slight boost on test accuracy over a typical full graph training regime.
  arXiv  Detail & Related papers  (2023-05-21T02:53:25Z)
• Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams [35.943447765433774]
  We propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream. We determine the weights of edges in a data-driven fashion, using a novel method based on reinforcement learning.
  arXiv  Detail & Related papers  (2022-11-13T03:01:34Z)
• From Spectral Graph Convolutions to Large Scale Graph Convolutional Networks [0.0]
  Graph Convolutional Networks (GCNs) have been shown to be a powerful concept that has been successfully applied to a large variety of tasks. We study the theory that paved the way to the definition of GCN, including related parts of classical graph theory.
  arXiv  Detail & Related papers  (2022-07-12T16:57:08Z)
• Condensing Graphs via One-Step Gradient Matching [50.07587238142548]
  We propose a one-step gradient matching scheme, which performs gradient matching for only one single step without training the network weights. Our theoretical analysis shows this strategy can generate synthetic graphs that lead to lower classification loss on real graphs. In particular, we are able to reduce the dataset size by 90% while approximating up to 98% of the original performance.
  arXiv  Detail & Related papers  (2022-06-15T18:20:01Z)
• Self-Supervised Representation Learning via Latent Graph Prediction [41.64774038444827]
  Self-supervised learning (SSL) of graph neural networks is emerging as a promising way of leveraging unlabeled data. We propose the LaGraph, a theoretically grounded predictive SSL framework based on latent graph prediction. Our experimental results demonstrate the superiority of LaGraph in performance and the robustness to decreasing of training sample size on both graph-level and node-level tasks.
  arXiv  Detail & Related papers  (2022-02-16T21:10:33Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.