Related papers: From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

URL: http://arxiv.org/abs/2205.15895v1
Date: Tue, 31 May 2022 15:44:29 GMT
Title: From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Authors: Dimitrios Mallis, Enrique Sanchez, Matt Bell and Georgios Tzimiropoulos
Abstract summary: This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. We validate our method on a variety of difficult datasets, including LS3D, BBCPose, Human3.6M and PennAction.
Score: 37.78933209094847
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where, departing from generic keypoints, a landmark detector and descriptor is trained to improve itself, tuning the keypoints into distinctive landmarks. To this end, we propose an iterative algorithm that alternates between producing new pseudo-labels through feature clustering and learning distinctive features for each pseudo-class through contrastive learning. With a shared backbone for the landmark detector and descriptor, the keypoint locations progressively converge to stable landmarks, filtering those less stable. Compared to previous works, our approach can learn points that are more flexible in terms of capturing large viewpoint changes. We validate our method on a variety of difficult datasets, including LS3D, BBCPose, Human3.6M and PennAction, achieving new state of the art results.

Related papers

Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling [3.255030588361124]
This paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition. A point cloud deep-learning paradigm is introduced to the action recognition. A novel deep neural network architecture called Structured Keypoint Pooling is proposed.
arXiv Detail & Related papers (2023-03-27T14:59:08Z)
Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations [81.02347863372364]
We present Point-Teaching, a weakly semi-supervised object detection framework. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points.
arXiv Detail & Related papers (2022-06-01T07:04:38Z)
Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction [11.164069907549756]
3D semantic keypoints are category-level semantic consistent points on 3D objects. We present an unsupervised method to generate consistent semantic keypoints from point clouds explicitly. To the best of our knowledge, the proposed method is the first to mine 3D semantic consistent keypoints from a mutual reconstruction view.
arXiv Detail & Related papers (2022-03-19T01:49:21Z)
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
arXiv Detail & Related papers (2022-01-06T08:54:47Z)
Pretrained equivariant features improve unsupervised landmark discovery [69.02115180674885]
We formulate a two-step unsupervised approach that overcomes this challenge by first learning powerful pixel-based features. Our method produces state-of-the-art results in several challenging landmark detection datasets.
arXiv Detail & Related papers (2021-04-07T05:42:11Z)
Keypoint Autoencoders: Learning Interest Points of Semantics [4.551313396927381]
We propose Keypoint Autoencoder, an unsupervised learning method for detecting keypoints. We encourage selecting sparse semantic keypoints by enforcing the reconstruction from keypoints to the original point cloud. A downstream task of classifying shape with sparse keypoints is conducted to demonstrate the distinctiveness of our selected keypoints.
arXiv Detail & Related papers (2020-08-11T03:43:18Z)
A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds [54.73161039445703]
We propose a novel self-training approach that enables a typical object detector trained only with point-level annotations. During training, we utilize the available point annotations to supervise the estimation of the center points of objects. Experimental results show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks.
arXiv Detail & Related papers (2020-07-25T02:14:42Z)
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation [85.96410825961966]
We argue that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries. To facilitate inference, we propose to instead perform regression from a set of points placed at more advantageous positions. We apply this proposed framework, called Point-Set Anchors, to object detection, instance segmentation, and human pose estimation.
arXiv Detail & Related papers (2020-07-06T15:59:56Z)

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