paper-with-me

Papers

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization

2021-04-19 · NeurIPS 2021 12 · Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung, Daniel Cohen-Or

Multilayer-perceptrons (MLP) are known to struggle with learning functions of high-frequencies, and in particular cases with wide frequency bands. We present a spatially adaptive progressive encoding (SAPE) scheme for input signals of MLP networks, which enables them to better fit a wide range of frequencies without sacrificing training stability or requiring any domain specific preprocessing. SAPE gradually unmasks signal components with increasing frequencies as a function of time and space. The progressive exposure of frequencies is monitored by a feedback loop throughout the neural optimization process, allowing changes to propagate at different rates among local spatial portions of the signal space. We demonstrate the advantage of SAPE on a variety of domains and applications, including regression of low dimensional signals and images, representation learning of occupancy networks, and a geometric task of mesh transfer between 3D shapes.

📄 PDF Abstract BibTeX arXiv:2104.09125

Code (1)

amirhertz/sape pytorch

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

A 2D Semantic-Aware Position Encoding for Vision Transformers

2025-05-14 · Xi Chen, Shiyang Zhou, Muqi Huang, Jiaxu Feng 외

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing positio…

PositionSemantic SimilaritySemantic Textual SimilarityTranslation

Ow\'oksape - An Online Language Learning Platform for Lakota

2020-05-01 · LREC 2020 5 · Jan Ullrich, Elliot Thornton, Peter Vieira, Logan Swango 외

This paper presents Ow{\'o}ksape, an online language learning platform for the under-resourced language Lakota. The Lakota language (LakÈŸ{\'o}tiyapi) is a Siouan language native to the United States with fewer than 2000…

Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation

2024-05-19 · Zejun Gu, Zhong-Qiu Zhao, Henghui Ding, Hao Shen 외

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of…

Knowledge DistillationPose Estimation

Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction

2024-12-06 · Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction …

Surface Reconstruction

Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation

2025-11-14 · Daxin Li, Yuanchao Bai, Kai Wang, Wenbo Zhao 외 arxiv

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, intro…

Image Compression