Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining

• URL: http://arxiv.org/abs/2504.20800v1
• Date: Tue, 29 Apr 2025 14:14:29 GMT
• Title: Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining
• Authors: Weizhen He, Yunfeng Yan, Shixiang Tang, Yiheng Deng, Yangyang Zhong, Pengxin Luo, Donglian Qi,
• Abstract summary: This paper improves the data scalability of human-centric pretraining methods.<n>We explore semantic information of RGB images in the frequency space by Discrete Cosine Transform (DCT)<n>We also propose new annotation denoising auxiliary tasks with keypoints and DCT maps to enforce the RGB image extractor.
• Score: 12.950323493528508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human-centric perception is the core of diverse computer vision tasks and has been a long-standing research focus. However, previous research studied these human-centric tasks individually, whose performance is largely limited to the size of the public task-specific datasets. Recent human-centric methods leverage the additional modalities, e.g., depth, to learn fine-grained semantic information, which limits the benefit of pretraining models due to their sensitivity to camera views and the scarcity of RGB-D data on the Internet. This paper improves the data scalability of human-centric pretraining methods by discarding depth information and exploring semantic information of RGB images in the frequency space by Discrete Cosine Transform (DCT). We further propose new annotation denoising auxiliary tasks with keypoints and DCT maps to enforce the RGB image extractor to learn fine-grained semantic information of human bodies. Our extensive experiments show that when pretrained on large-scale datasets (COCO and AIC datasets) without depth annotation, our model achieves better performance than state-of-the-art methods by +0.5 mAP on COCO, +1.4 PCKh on MPII and -0.51 EPE on Human3.6M for pose estimation, by +4.50 mIoU on Human3.6M for human parsing, by -3.14 MAE on SHA and -0.07 MAE on SHB for crowd counting, by +1.1 F1 score on SHA and +0.8 F1 score on SHA for crowd localization, and by +0.1 mAP on Market1501 and +0.8 mAP on MSMT for person ReID. We also validate the effectiveness of our method on MPII+NTURGBD datasets

Related papers

• A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning [67.72413262980272]
  Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear.<n>We develop SlotMIM, a method that induces object-centric representations by introducing a semantic bottleneck.<n>Our approach achieves significant improvements over prior work in image recognition, scene understanding, and robot learning evaluations.
  arXiv  Detail & Related papers  (2025-03-10T06:18:31Z)
• UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning [29.037799937729687]
  2D and 3D Human Pose Estimation (HPE) are two critical perceptual tasks in computer vision. We propose UniHPE, a unified Human Pose Estimation pipeline, which aligns features from all three modalities. Our proposed method holds immense potential to advance the field of computer vision and contribute to various applications.
  arXiv  Detail & Related papers  (2023-11-24T21:55:34Z)
• HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception [97.55089867970874]
  We introduce masked image modeling (MIM) as a pre-training approach for this task. Motivated by this insight, we incorporate an intuitive human structure prior - human parts - into pre-training. This encourages the model to concentrate more on body structure information during pre-training, yielding substantial benefits across a range of human-centric perception tasks.
  arXiv  Detail & Related papers  (2023-10-31T17:56:11Z)
• MIMIC: Masked Image Modeling with Image Correspondences [29.8154890262928]
  Current methods for building effective pretraining datasets rely on annotated 3D meshes, point clouds, and camera parameters from simulated environments. We propose a pretraining dataset-curation approach that does not require any additional annotations. Our method allows us to generate multi-view datasets from both real-world videos and simulated environments at scale.
  arXiv  Detail & Related papers  (2023-06-27T00:40:12Z)
• Delving Deeper into Data Scaling in Masked Image Modeling [145.36501330782357]
  We conduct an empirical study on the scaling capability of masked image modeling (MIM) methods for visual recognition. Specifically, we utilize the web-collected Coyo-700M dataset. Our goal is to investigate how the performance changes on downstream tasks when scaling with different sizes of data and models.
  arXiv  Detail & Related papers  (2023-05-24T15:33:46Z)
• Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition [71.91734471596433]
  Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. This paper proposes using datasets intended for human-pose estimation as a source for transfer learning.
  arXiv  Detail & Related papers  (2022-12-02T18:19:36Z)
• KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences [77.56222946832237]
  We present a novel framework to detect the densepose of multiple people in an image. The proposed method, which we refer to Knowledge Transfer Network (KTN), tackles two main problems. It simultaneously maintains feature resolution and suppresses background pixels, and this strategy results in substantial increase in accuracy.
  arXiv  Detail & Related papers  (2022-06-21T03:11:37Z)
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training [102.15325936477362]
  We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only 1% slower)
  arXiv  Detail & Related papers  (2020-11-18T08:42:32Z)
• SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data [7.053519629075887]
  We present a technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain generalization for the 2.5DPose estimation task and the 3D human surface normal estimation task. Our approach is complementary to existing domain-adaptation techniques and can be applied to other dense per-pixel pose estimation problems.
  arXiv  Detail & Related papers  (2020-07-30T14:59:38Z)

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.