paper-with-me

Papers

HydraNets: Specialized Dynamic Architectures for Efficient Inference

2018-06-01 · CVPR 2018 6 · Ravi Teja Mullapudi, William R. Mark, Noam Shazeer, Kayvon Fatahalian

There is growing interest in improving the design of deep network architectures to be both accurate and low cost. This paper explores semantic specialization as a mechanism for improving the computational efficiency (accuracy-per-unit-cost) of inference in the context of image classification. Specifically, we propose a network architecture template called HydraNet, which enables state-of-the-art architectures for image classification to be transformed into dynamic architectures which exploit conditional execution for efficient inference. HydraNets are wide networks containing distinct components specialized to compute features for visually similar classes, but they retain efficiency by dynamically selecting only a small number of components to evaluate for any one input image. This design is made possible by a soft gating mechanism that encourages component specialization during training and accurately performs component selection during inference. We evaluate the HydraNet approach on both the CIFAR-100 and ImageNet classification tasks. On CIFAR, applying the HydraNet template to the ResNet and DenseNet family of models reduces inference cost by 2-4x while retaining the accuracy of the baseline architectures. On ImageNet, applying the HydraNet template improves accuracy up to 2.5% when compared to an efficient baseline architecture with similar inference cost.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationComputational EfficiencyGeneral Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Dense Block A Dense Block is a module used in convolutional neural networks that connects *all layers* (with matching feature-map sizes) directly with each other. It was originally…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
XRP Customer Service Number +1-833-534-1729 설명 없음
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…

Similar Papers 제목 키워드 기반

Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning

2025-11-11 · Mehrdad Zakershahrak arxiv

Reinforcement learning has traditionally focused on a singular objective: learning policies that select actions to maximize reward. We challenge this paradigm by asking: what if we explicitly architected RL systems as in…

Reinforcement Learning

ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns

2026-02-17 · Ziyu Zhao, Tong Zhu, Zhi Zhang, Tiantian Fan 외 arxiv

Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promis…

Computational Efficiency

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

2025-09-24 · Sampurna Roy, Ayan Sar, Anurag Kaushish, Kanav Gupta 외 arxiv

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as …

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs

2025-08-20 · Ruyi Ding, Tianhong Xu, Xinyi Shen, Aidong Adam Ding 외 arxiv

The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to sc…

Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU

2026-04-16 · Jevin Jiang, Ying Chen, Blake A. Hechtman, Fenghui Zhang 외 arxiv

Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizing both performance and total cost of ownership (TCO). However, existi…