Pretrained equivariant features improve unsupervised landmark discovery
- URL: http://arxiv.org/abs/2104.02925v1
- Date: Wed, 7 Apr 2021 05:42:11 GMT
- Title: Pretrained equivariant features improve unsupervised landmark discovery
- Authors: Rahul Rahaman, Atin Ghosh and Alexandre H. Thiery
- Abstract summary: 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.
- Score: 69.02115180674885
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Locating semantically meaningful landmark points is a crucial component of a
large number of computer vision pipelines. Because of the small number of
available datasets with ground truth landmark annotations, it is important to
design robust unsupervised and semi-supervised methods for landmark detection.
Many of the recent unsupervised learning methods rely on the equivariance
properties of landmarks to synthetic image deformations. Our work focuses on
such widely used methods and sheds light on its core problem, its inability to
produce equivariant intermediate convolutional features. This finding leads us
to formulate a two-step unsupervised approach that overcomes this challenge by
first learning powerful pixel-based features and then use the pre-trained
features to learn a landmark detector by the traditional equivariance method.
Our method produces state-of-the-art results in several challenging landmark
detection datasets such as the BBC Pose dataset and the Cat-Head dataset. It
performs comparably on a range of other benchmarks.
Related papers
- FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks [44.54301473673582]
We propose the first foundation model-enabled one-shot landmark detection (FM-OSD) framework for accurate landmark detection in medical images.
By using solely a single template image, our method demonstrates significant superiority over strong state-of-the-art one-shot landmark detection methods.
arXiv Detail & Related papers (2024-07-07T15:37:02Z) - Unsupervised learning based object detection using Contrastive Learning [6.912349403119665]
We introduce a groundbreaking method for training single-stage object detectors through unsupervised/self-supervised learning.
Our state-of-the-art approach has the potential to revolutionize the labeling process, substantially reducing the time and cost associated with manual annotation.
We pioneer the concept of intra-image contrastive learning alongside inter-image counterparts, enabling the acquisition of crucial location information.
arXiv Detail & Related papers (2024-02-21T01:44:15Z) - Towards Multi-domain Face Landmark Detection with Synthetic Data from
Diffusion model [27.307563102526192]
deep learning-based facial landmark detection for in-the-wild faces has achieved significant improvement.
There are still challenges in face landmark detection in other domains (e.g. cartoon, caricature, etc)
We design a two-stage training approach that effectively leverages limited datasets and the pre-trained diffusion model.
Our results demonstrate that our method outperforms existing methods on multi-domain face landmark detection.
arXiv Detail & Related papers (2024-01-24T02:35:32Z) - Weakly-supervised deepfake localization in diffusion-generated images [4.548755617115687]
We propose a weakly-supervised localization problem based on the Xception network as the backbone architecture.
We show that the best performing detection method (based on local scores) is less sensitive to the looser supervision than to the mismatch in terms of dataset or generator.
arXiv Detail & Related papers (2023-11-08T10:27:36Z) - Domain Adaptive Synapse Detection with Weak Point Annotations [63.97144211520869]
We present AdaSyn, a framework for domain adaptive synapse detection with weak point annotations.
In the WASPSYN challenge at I SBI 2023, our method ranks the 1st place.
arXiv Detail & Related papers (2023-08-31T05:05:53Z) - Weakly-supervised 3D Pose Transfer with Keypoints [57.66991032263699]
Main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with different topologies.
We propose a novel weakly-supervised keypoint-based framework to overcome these difficulties.
arXiv Detail & Related papers (2023-07-25T12:40:24Z) - From Keypoints to Object Landmarks via Self-Training Correspondence: A
novel approach to Unsupervised Landmark Discovery [37.78933209094847]
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.
arXiv Detail & Related papers (2022-05-31T15:44:29Z) - LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of
Feature Similarity [49.84167231111667]
Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image.
We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion.
We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
arXiv Detail & Related papers (2022-04-06T17:48:18Z) - 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) - Stance Detection Benchmark: How Robust Is Your Stance Detection? [65.91772010586605]
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim.
We introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning setting.
Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets.
arXiv Detail & Related papers (2020-01-06T13:37:51Z)
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.