TreeNet: A lightweight One-Shot Aggregation Convolutional Network
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TreeNet: A Light Weight Model for Low Bitrate Image Compression
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 CompressionWhy M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
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…
DiversityTreeNet: Layered Decision Ensembles
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 LearningCost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
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 correspondenceCross Spline Net and a Unified World
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…