English
Related papers

Related papers: TCDesc: Learning Topology Consistent Descriptors

200 papers

In the context of multi-view clustering, graph learning is recognized as a crucial technique, which generally involves constructing an adaptive neighbor graph based on probabilistic neighbors, and then learning a consensus graph for…

Machine Learning · Computer Science 2025-07-08 Long Shi , Lei Cao , Yunshan Ye , Yu Zhao , Badong Chen

In linear distance metric learning, we are given data in one Euclidean metric space and the goal is to find an appropriate linear map to another Euclidean metric space which respects certain distance conditions as much as possible. In this…

Machine Learning · Computer Science 2023-12-22 Meysam Alishahi , Anna Little , Jeff M. Phillips

The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs). Recognizing the limitations of traditional complexity measures, the LLC leverages Singular Learning Theory (SLT), which has…

Machine Learning · Statistics 2024-10-02 Edmund Lau , Zach Furman , George Wang , Daniel Murfet , Susan Wei

Visual localization to compute 6DoF camera pose from a given image has wide applications such as in robotics, virtual reality, augmented reality, etc. Two kinds of descriptors are important for the visual localization. One is global…

Computer Vision and Pattern Recognition · Computer Science 2020-09-24 Pengju Zhang , Yihong Wu , Bingxi Liu

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…

Computation and Language · Computer Science 2022-10-20 Malte Ostendorff , Nils Rethmeier , Isabelle Augenstein , Bela Gipp , Georg Rehm

Temporal graph neural networks Tgnn have exhibited state-of-art performance in future-link prediction tasks. Training of these TGNNs is enumerated by uniform random sampling based unsupervised loss. During training, in the context of a…

Machine Learning · Computer Science 2024-02-16 Shubham Gupta , Srikanta Bedathur

Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Zhengwen Li , Xiabi Liu

We tackle the problem of finding accurate and robust keypoint correspondences between images. We propose a learning-based approach to guide local feature matches via a learned approximate image matching. Our approach can boost the results…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 François Darmon , Mathieu Aubry , Pascal Monasse

Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Laurin Lux , Alexander H. Berger , Alexander Weers , Nico Stucki , Daniel Rueckert , Ulrich Bauer , Johannes C. Paetzold

Capturing the global topology of an image is essential for proposing an accurate segmentation of its domain. However, most of existing segmentation methods do not preserve the initial topology of the given input, which is detrimental for…

Computer Vision and Pattern Recognition · Computer Science 2022-08-19 Minh On Vu Ngoc , Yizi Chen , Nicolas Boutry , Jonathan Fabrizio , Clement Mallet

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the…

Machine Learning · Statistics 2021-11-05 Milad Sikaroudi , Benyamin Ghojogh , Fakhri Karray , Mark Crowley , H. R. Tizhoosh

Standard deep learning models for image segmentation cannot guarantee topology accuracy, failing to preserve the correct number of connected components or structures. This, in turn, affects the quality of the segmentations and compromises…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Juan Miguel Valverde , Dim P. Papadopoulos , Rasmus Larsen , Anders Bjorholm Dahl

This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Sungyeon Kim , Dongwon Kim , Minsu Cho , Suha Kwak

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Hong Xuan , Xi Chen

Dimensionality reduction techniques map values from a high dimensional space to one with a lower dimension. The result is a space which requires less physical memory and has a faster distance calculation. These techniques are widely used…

Information Retrieval · Computer Science 2024-02-14 Richard Connor , Lucia Vadicamo

Computational topology provides a tool, persistent homology, to extract quantitative descriptors from structured objects (images, graphs, point clouds, etc). These descriptors can then be involved in optimization problems, typically as a…

Computational Geometry · Computer Science 2026-03-27 Mathieu Carriere , Yuichi Ike , Théo Lacombe , Naoki Nishikawa

Text-guided image retrieval is to incorporate conditional text to better capture users' intent. Traditionally, the existing methods focus on minimizing the embedding distances between the source inputs and the targeted image, using the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Junyang Chen , Hanjiang Lai

Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuous-valued loss…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 Xiaoling Hu , Li Fuxin , Dimitris Samaras , Chao Chen

We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph…

Computation and Language · Computer Science 2019-04-15 Andrey Kutuzov , Mohammad Dorgham , Oleksiy Oliynyk , Chris Biemann , Alexander Panchenko

To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance…

Computer Vision and Pattern Recognition · Computer Science 2017-07-28 Ben Harwood , Vijay Kumar B G , Gustavo Carneiro , Ian Reid , Tom Drummond