paper-with-me

홈 › Papers

Expanding-and-Shrinking Binary Neural Networks

2025-03-31 · Xulong Shi, Caiyi Sun, Zhi Qi, Liu Hao, Xiaodong Yang

While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of weights and activations, the possible values of each entry in the feature maps generated by BNNs are strongly constrained. To tackle this limitation, we propose the expanding-and-shrinking operation, which enhances binary feature maps with negligible increase of computation complexity, thereby strengthening the representation capacity. Extensive experiments conducted on multiple benchmarks reveal that our approach generalizes well across diverse applications ranging from image classification, object detection to generative diffusion model, while also achieving remarkable improvement over various leading binarization algorithms based on different architectures including both CNNs and Transformers.

📄 PDF Abstract BibTeX arXiv:2503.23709

Code (1)

imfinethanks/esbnn 공식 구현 pytorch

Tasks

Binarizationimage-classificationImage Classificationobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels

2020-03-22 · Zan Shen, Jiang Qian, Bojin Zhuang, Shaojun Wang 외

One-Shot methods have evolved into one of the most popular methods in Neural Architecture Search (NAS) due to weight sharing and single training of a supernet. However, existing methods generally suffer from two issues: …

Neural Architecture Search

A new neural-network-based model for measuring the strength of a pseudorandom binary sequence

2019-10-09 · Ahmed Alamer, Ben Soh

Maximum order complexity is an important tool for measuring the nonlinearity of a pseudorandom sequence. There is a lack of tools for predicting the strength of a pseudorandom binary sequence in an effective and efficien…

Incremental and Decremental Fuzzy Bounded Twin Support Vector Machine

2019-07-22 · Alexandre Reeberg de Mello, Marcelo Ricardo Stemmer, Alessandro Lameiras Koerich

In this paper we present an incremental variant of the Twin Support Vector Machine (TWSVM) called Fuzzy Bounded Twin Support Vector Machine (FBTWSVM) to deal with large datasets and learning from data streams. We combine…

General ClassificationRobust classification

MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

2017-11-18 · CVPR 2018 6 · Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen 외

We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expan…

Neural Architecture Search

Manifold Micro-Surgery with Linearly Nearly Euclidean Metrics

2021-09-29 · Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu

The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular. However, in most cases, the Rich flow tends to develop singularities and lead to divergence of the solution. In this paper, we pro…