paper-with-me

홈 › Papers

TreeNet: A lightweight One-Shot Aggregation Convolutional Network

2021-09-25 · Lu Rao

The architecture of deep convolutional networks (CNNs) has evolved for years, becoming more accurate and faster. However, it is still challenging to design reasonable network structures that aim at obtaining the best accuracy under a limited computational budget. In this paper, we propose a Tree block, named after its appearance, which extends the One-Shot Aggregation (OSA) module while being more lightweight and flexible. Specifically, the Tree block replaces each of the $3\times3$ Conv layers in OSA into a stack of shallow residual block (SRB) and $1\times1$ Conv layer. The $1\times1$ Conv layer is responsible for dimension increasing and the SRB is fed into the next step. By doing this, when aggregating the same number of subsequent feature maps, the Tree block has a deeper network structure while having less model complexity. In addition, residual connection and efficient channel attention(ECA) is added to the Tree block to further improve the performance of the network. Based on the Tree block, we build efficient backbone models calling TreeNets. TreeNet has a similar network architecture to ResNet, making it flexible to replace ResNet in various computer vision frameworks. We comprehensively evaluate TreeNet on common-used benchmarks, including ImageNet-1k for classification, MS COCO for object detection, and instance segmentation. Experimental results demonstrate that TreeNet is more efficient and performs favorably against the current state-of-the-art backbone methods.

📄 PDF Abstract BibTeX arXiv:2109.12342

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

TreeNet: A Light Weight Model for Low Bitrate Image Compression

2025-12-18 · Mahadev Prasad Panda, Purnachandra Rao Makkena, Srivatsa Prativadibhayankaram, Siegfried Fößel 외 arxiv

Reducing computational complexity remains a critical challenge for the widespread adoption of learning-based image compression techniques. In this work, we propose TreeNet, a novel low-complexity image compression model …

Image Compression

Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks

2015-11-19 · Stefan Lee, Senthil Purushwalkam, Michael Cogswell, David Crandall 외

Convolutional Neural Networks have achieved state-of-the-art performance on a wide range of tasks. Most benchmarks are led by ensembles of these powerful learners, but ensembling is typically treated as a post-hoc proced…

Diversity

TreeNet: Layered Decision Ensembles

2025-10-07 · Zeshan Khan arxiv

Within the domain of medical image analysis, three distinct methodologies have demonstrated commendable accuracy: Neural Networks, Decision Trees, and Ensemble-Based Learning Algorithms, particularly in the specialized c…

Ensemble Learning

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

2022-07-22 · Sunghwan Hong, Seokju Cho, Jisu Nam, Stephen Lin 외

This paper presents a novel cost aggregation network, called Volumetric Aggregation with Transformers (VAT), for few-shot segmentation. The use of transformers can benefit correlation map aggregation through self-attenti…

DecoderFew-Shot Semantic SegmentationInductive BiasSemantic correspondence

Cross Spline Net and a Unified World

2024-10-24 · Linwei Hu, Ye Jin Choi, Vijayan N. Nair

In today's machine learning world for tabular data, XGBoost and fully connected neural network (FCNN) are two most popular methods due to their good model performance and convenience to use. However, they are highly comp…