paper-with-me

홈 › Papers

Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture

2018-12-03 · Shichao Li, Xin Yang, Tim Cheng

We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility. A stochastic routing framework as used by recent deep neural decision/regression forests is incorporated, but we remove the need to evaluate unnecessary computation paths by utilizing a different topology and introducing a probabilistic pruning technique. We also show a specified version of DHM (DSHM) for efficiency, which inherits the sparse feature extraction process as in traditional decision tree with pixel-difference feature. To achieve sparse feature extraction, we propose to utilize sparse convolution operation in DSHM and show one possibility of introducing sparse convolution kernels by using local binary convolution layer. DHM can be applied to both classification and regression problems, and we validate it on standard image classification and face alignment tasks to show its advantages over past architectures.

📄 PDF Abstract BibTeX arXiv:1812.00647

Code (0)

등록된 구현이 없습니다.

Tasks

Face AlignmentGeneral Classificationimage-classificationImage ClassificationregressionRepresentation Learning

Methods 이 논문이 사용한 방법론

Pruning 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…

Similar Papers 제목 키워드 기반

Divide-and-Conquer with Sequential Monte Carlo

2014-06-19 · Fredrik Lindsten, Adam M. Johansen, Christian A. Naesseth, Bonnie Kirkpatrick 외

We propose a novel class of Sequential Monte Carlo (SMC) algorithms, appropriate for inference in probabilistic graphical models. This class of algorithms adopts a divide-and-conquer approach based upon an auxiliary tree…

Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affective Computing

2019-07-01 · ACL 2019 7 · Sijie Mai, Haifeng Hu, Songlong Xing

We propose a general strategy named {`}divide, conquer and combine{'} for multimodal fusion. Instead of directly fusing features at holistic level, we conduct fusion hierarchically so that both local and global interacti…

WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolution

2020-10-07 · Vikram Singh, Anurag Mittal

Divide and conquer is an established algorithm design paradigm that has proven itself to solve a variety of problems efficiently. However, it is yet to be fully explored in solving problems with a neural network, particu…

Image Super-ResolutionSuper-Resolution

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

2025-05-26 · Zican Hu, Wei Liu, Xiaoye Qu, Xiangyu Yue 외

While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-rewa…

Decision MakingHierarchical Reinforcement Learning

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need

2025-06-18 · Zhouhong Gu, Xiaoxuan Zhu, Yin Cai, Hao Shen 외

Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture…

GSM8KHumanEvalLarge Language ModelMath+1