paper-with-me

홈 › Papers

An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching

2019-04-12 · René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker

Training a deep neural network is a non-trivial task. Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to get the most out of a model. In this study, we perform a set of experiments all related to these issues. The model for which different training strategies are investigated is the recently presented SDC descriptor network (stacked dilated convolution). It is used to describe images on pixel-level for dense matching tasks. Our work analyzes SDC in more detail, validates some best practices for training deep neural networks, and provides insights into training with multiple domain data.

📄 PDF Abstract BibTeX arXiv:1904.06167

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep ViT Features as Dense Visual Descriptors

2021-12-10 · Shir Amir, Yossi Gandelsman, Shai Bagon, Tali Dekel

We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when extractedfrom a self-supervised ViT mode…

Feature UpsamplingSemantic correspondence

Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations

2022-10-17 · Jong Hak Moon, Wonjae Kim, Edward Choi

Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations ha…

Contrastive LearningLinear evaluation

A Universal Dense Football Event Representation Based on TabTransformer

2026-06-08 · Weiran Yang, Daniel Memmert, Maximilian Klemp-Weins arxiv

Football event data constitute a rich spatiotemporal source for quantitative analysis of player actions in team sports. These datasets contain heterogeneous features, combining continuous location coordinates with catego…

Federated Graph Condensation with Information Bottleneck Principles

2024-05-07 · Bo Yan, Sihao He, Cheng Yang, Shang Liu 외

Graph condensation (GC), which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has benefited various graph learning tasks. However, existing GC methods rely on c…

Graph LearningInference AttackMembership Inference AttackPrivacy Preserving

Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News

2017-04-03 · Yinfei Yang, Ani Nenkova

Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all…

ArticlesQuestion Answering