SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

• URL: http://arxiv.org/abs/2404.03518v1
• Date: Thu, 4 Apr 2024 15:23:14 GMT
• Title: SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
• Authors: Sichen Chen, Yingyi Zhang, Siming Huang, Ran Yi, Ke Fan, Ruixin Zhang, Peixian Chen, Jun Wang, Shouhong Ding, Lizhuang Ma,
• Abstract summary: We introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models. SDPose-T obtains 69.7% mAP with 4.4M parameters and 1.8 GFLOPs, while SDPose-S-V2 obtains 73.5% mAP on the MSCOCO validation dataset.
• Score: 53.675725490807615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to deploy on edge computing platforms. Those transformer-based models that require fewer resources are prone to under-fitting due to their smaller scale and thus perform notably worse than their larger counterparts. Given this conundrum, we introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models. To mitigate the problem of under-fitting, we design a transformer module named Multi-Cycled Transformer(MCT) based on multiple-cycled forwards to more fully exploit the potential of small model parameters. Further, in order to prevent the additional inference compute-consuming brought by MCT, we introduce a self-distillation scheme, extracting the knowledge from the MCT module to a naive forward model. Specifically, on the MSCOCO validation dataset, SDPose-T obtains 69.7% mAP with 4.4M parameters and 1.8 GFLOPs. Furthermore, SDPose-S-V2 obtains 73.5% mAP on the MSCOCO validation dataset with 6.2M parameters and 4.7 GFLOPs, achieving a new state-of-the-art among predominant tiny neural network methods. Our code is available at https://github.com/MartyrPenink/SDPose.

Related papers

• Pre-training Point Cloud Compact Model with Partial-aware Reconstruction [51.403810709250024]
  We present a pre-trained Point cloud Compact Model with Partial-aware textbfReconstruction, named Point-CPR. Our model exhibits strong performance across various tasks, especially surpassing the leading MPM-based model PointGPT-B with only 2% of its parameters.
  arXiv  Detail & Related papers  (2024-07-12T15:18:14Z)
• LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling [47.94285833315427]
  We propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density.
  arXiv  Detail & Related papers  (2024-05-27T13:19:23Z)
• SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation [74.07836010698801]
  We propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods.
  arXiv  Detail & Related papers  (2024-04-23T17:59:59Z)
• MatFormer: Nested Transformer for Elastic Inference [94.1789252941718]
  MatFormer is a nested Transformer architecture designed to offer elasticity in a variety of deployment constraints. We show that a 2.6B decoder-only MatFormer language model (MatLM) allows us to extract smaller models spanning from 1.5B to 2.6B. We also observe that smaller encoders extracted from a universal MatFormer-based ViT (MatViT) encoder preserve the metric-space structure for adaptive large-scale retrieval.
  arXiv  Detail & Related papers  (2023-10-11T17:57:14Z)
• Quantized Transformer Language Model Implementations on Edge Devices [1.2979415757860164]
  Large-scale transformer-based models like the Bidirectional Representations from Transformers (BERT) are widely used for Natural Language Processing (NLP) applications. These models are initially pre-trained with a large corpus with millions of parameters and then fine-tuned for a downstream NLP task. One of the major limitations of these large-scale models is that they cannot be deployed on resource-constrained devices due to their large model size and increased inference latency.
  arXiv  Detail & Related papers  (2023-10-06T01:59:19Z)
• Element-Wise Attention Layers: an option for optimization [0.0]
  It's proposed a new method of attention mechanism that adapts the Dot-Product Attention to become element-wise through the use of arrays multiplications. The results show that this mechanism allows for an accuracy of 92% of the VGG-like counterpart in Fashion MNIST dataset, while reducing the number of parameters in 97%.
  arXiv  Detail & Related papers  (2023-02-10T19:50:34Z)
• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm [111.17100512647619]
  This paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) We propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2022-06-19T04:49:35Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)

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.