Towards Zero-Shot Interpretable Human Recognition: A 2D-3D Registration Framework
- URL: http://arxiv.org/abs/2403.06658v2
- Date: Wed, 26 Jun 2024 13:01:55 GMT
- Title: Towards Zero-Shot Interpretable Human Recognition: A 2D-3D Registration Framework
- Authors: Henrique Jesus, Hugo Proença,
- Abstract summary: It is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts)
This paper describes the first recognition framework/strategy that aims at addressing the three weaknesses simultaneously.
- Score: 16.15084484295732
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts). To the best of our knowledge, this paper describes the first recognition framework/strategy that aims at addressing the three weaknesses simultaneously. At first, it relies exclusively in synthetic samples for learning purposes. Instead of requiring a large amount and variety of samples for each subject, the idea is to exclusively enroll a 3D point cloud per identity. Then, using generative strategies, we synthesize a very large (potentially infinite) number of samples, containing all the desired covariates (poses, clothing, distances, perspectives, lighting, occlusions,...). Upon the synthesizing method used, it is possible to adapt precisely to different kind of domains, which accounts for generalization purposes. Such data are then used to learn a model that performs local registration between image pairs, establishing positive correspondences between body parts that are the key, not only to recognition (according to cardinality and distribution), but also to provide an interpretable description of the response (e.g.: "both samples are from the same person, as they have similar facial shape, hair color and legs thickness").
Related papers
- Label-Efficient 3D Brain Segmentation via Complementary 2D Diffusion Models with Orthogonal Views [10.944692719150071]
We propose a novel 3D brain segmentation approach using complementary 2D diffusion models.
Our goal is to achieve reliable segmentation quality without requiring complete labels for each individual subject.
arXiv Detail & Related papers (2024-07-17T06:14:53Z) - Separating common from salient patterns with Contrastive Representation
Learning [2.250968907999846]
Contrastive Analysis aims at separating common factors of variation between two datasets.
Current models based on Variational Auto-Encoders have shown poor performance in learning semantically-expressive representations.
We propose to leverage the ability of Contrastive Learning to learn semantically expressive representations well adapted for Contrastive Analysis.
arXiv Detail & Related papers (2024-02-19T08:17:13Z) - Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly
Supervised 3D Visual Grounding [58.924180772480504]
3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query.
We propose to leverage weakly supervised annotations to learn the 3D visual grounding model.
We design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner.
arXiv Detail & Related papers (2023-07-18T13:49:49Z) - Advancing 3D finger knuckle recognition via deep feature learning [51.871256510747465]
Contactless 3D finger knuckle patterns have emerged as an effective biometric identifier due to its discriminativeness, visibility from a distance, and convenience.
Recent research has developed a deep feature collaboration network which simultaneously incorporates intermediate features from deep neural networks with multiple scales.
This paper advances this approach by investigating the possibility of learning a discriminative feature vector with the least possible dimension for representing 3D finger knuckle images.
arXiv Detail & Related papers (2023-01-07T20:55:16Z) - Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA)
First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features.
Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
arXiv Detail & Related papers (2022-09-27T15:50:31Z) - Can Shadows Reveal Biometric Information? [48.3561395627331]
We show that the biometric information leakage from shadows can be sufficient for reliable identity inference under representative scenarios.
We then develop a learning-based method that demonstrates this phenomenon in real settings.
arXiv Detail & Related papers (2022-09-21T02:36:32Z) - 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) - A Transformer-Based Contrastive Learning Approach for Few-Shot Sign
Language Recognition [0.0]
We propose a novel Contrastive Transformer-based model, which demonstrate to learn rich representations from body key points sequences.
Experiments showed that the model could generalize well and achieved competitive results for sign classes never seen in the training process.
arXiv Detail & Related papers (2022-04-05T11:42:55Z) - Symbiotic Adversarial Learning for Attribute-based Person Search [86.7506832053208]
We present a symbiotic adversarial learning framework, called SAL.Two GANs sit at the base of the framework in a symbiotic learning scheme.
Specifically, two different types of generative adversarial networks learn collaboratively throughout the training process.
arXiv Detail & Related papers (2020-07-19T07:24:45Z)
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.