Filters








20,474 Hits in 2.8 sec

Fine-Grained Neural Architecture Search [article]

Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee
<span title="2019-11-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature  ...  FGNAS runs efficiently in spite of significantly large search space compared to other methods because it trains networks end-to-end by a stochastic gradient descent method.  ...  Figure 1 illustrates the proposed fine-grained neural architecture search (FGNAS) approach, where our per-channel search algorithm generates a feature map given by a composition of multiple operations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07478v1">arXiv:1911.07478v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zbx4p5ogdjh55huoyjoavti2nu">fatcat:zbx4p5ogdjh55huoyjoavti2nu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904061022/https://arxiv.org/pdf/1911.07478v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/97/71/9771bf91e6fa4eea1b4de308b6b5db4239757982.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07478v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

AtomNAS: Fine-Grained End-to-End Neural Architecture Search [article]

Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan Yuille, Jianchao Yang
<span title="2020-02-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Search space design is very critical to neural architecture search (NAS) algorithms.  ...  We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms.  ...  ATOMNAS We formulate our neural architecture search method in a fine-grained search space with the atomic block used as the basic search unit.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.09640v2">arXiv:1912.09640v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qyjyg33dkvc53pglyppjrnee44">fatcat:qyjyg33dkvc53pglyppjrnee44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321111800/https://arxiv.org/pdf/1912.09640v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.09640v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining [article]

Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, Joseph E. Gonzalez
<span title="2021-03-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts.  ...  To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously.  ...  Fine-grained search improvements.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.02049v3">arXiv:2006.02049v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pia3albp6nebpohwhtnxgwwb7m">fatcat:pia3albp6nebpohwhtnxgwwb7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200610110542/https://arxiv.org/pdf/2006.02049v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.02049v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

FGATR-Net: Automatic Network Architecture Design for Fine-Grained Aircraft Type Recognition in Remote Sensing Images

Wei Liang, Jihao Li, Wenhui Diao, Xian Sun, Kun Fu, Yirong Wu
<span title="2020-12-21">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
In this paper, inspired by Neural Architecture Search (NAS), we explore a novel differentiable automatic architecture design framework for fine-grained aircraft type recognition in remote sensing images  ...  When all differentiable search phases are finished, the searched model called Fine-Grained Aircraft Type Recognition Net (FGATR-Net) is obtained.  ...  Conclusions In this article, a novel automatic architecture design framework for remote sensing fine-grained aircraft type recognition is firstly explored.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12244187">doi:10.3390/rs12244187</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4m37q73qkbbmtexemzfoa2aey4">fatcat:4m37q73qkbbmtexemzfoa2aey4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201224085153/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-12-04187/article_deploy/remotesensing-12-04187.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/44/9c/449c1695836d2b328cc4265bd8193a706fc02662.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12244187"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

EfficientTDNN: Efficient Architecture Search for Speaker Recognition [article]

Rui Wang, Zhihua Wei, Haoran Duan, Shouling Ji, Yang Long, Zhen Hong
<span title="2021-11-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken  ...  In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm.  ...  Neural Architecture Search The NAS technique provides a systematic methodology that designs neural architecture automatically. Zoph et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.13581v4">arXiv:2103.13581v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rwmzhvfdubfapjl5mldbg2ulkm">fatcat:rwmzhvfdubfapjl5mldbg2ulkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211130011647/https://arxiv.org/pdf/2103.13581v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.13581v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Full-attention based Neural Architecture Search using Context Auto-regression [article]

Yuan Zhou, Haiyang Wang, Shuwei Huo, Boyu Wang
<span title="2021-11-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Meanwhile, neural architecture search (NAS) has significantly advanced the automatic design of neural architectures.  ...  To verify the efficacy of the proposed methods, we conducted extensive experiments on various learning tasks, including image classification, fine-grained image recognition, and zero-shot image retrieval  ...  To eliminate such extensive engineering, neural architecture search (NAS) methods [1] - [4] have been proposed to automate the design of neural architectures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.07139v1">arXiv:2111.07139v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/46dhlcsuzffezckmrv6hf2sf74">fatcat:46dhlcsuzffezckmrv6hf2sf74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211201150944/https://arxiv.org/pdf/2111.07139v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/19/7d19df182c74cf5d41adb94d6b6ca9d34ccf6b24.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.07139v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fine-Grained Stochastic Architecture Search [article]

Shraman Ray Chaudhuri, Elad Eban, Hanhan Li, Max Moroz, Yair Movshovitz-Attias
<span title="2020-06-17">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce Fine-Grained Stochastic Architecture Search (FiGS), a differentiable search method that searches over a much larger set of candidate architectures.  ...  Differentiable neural architecture search (DNAS) methods reduce the search cost but explore a limited subspace of candidate architectures.  ...  Related Work Neural architecture search (NAS) automates the design of neural net models with machine learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09581v1">arXiv:2006.09581v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m6jjb77ckfcpdbwzxfgfors2jq">fatcat:m6jjb77ckfcpdbwzxfgfors2jq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623193134/https://arxiv.org/pdf/2006.09581v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09581v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

VEGA: Towards an End-to-End Configurable AutoML Pipeline [article]

Bochao Wang, Hang Xu, Jiajin Zhang, Chen Chen, Xiaozhi Fang, Yixing Xu, Ning Kang, Lanqing Hong, Chenhan Jiang, Xinyue Cai, Jiawei Li, Fengwei Zhou (+12 others)
<span title="2020-11-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Architecture Search (NAS), Hyperparameter Optimization (HPO), Auto Data Augmentation, Model Compression, and Fully Train. b) To support a variety of search algorithms and tasks, we design a novel fine-grained  ...  we present VEGA, an efficient and comprehensive AutoML framework that is compatible and optimized for multiple hardware platforms. a) The VEGA pipeline integrates various modules of AutoML, including Neural  ...  With fine-grained search space introduced in Section 4.2, model compression can be view as a special case of neural architecture search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.01507v4">arXiv:2011.01507v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ghypdxt3cjbm7jk32dwhlajixm">fatcat:ghypdxt3cjbm7jk32dwhlajixm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201109080803/https://arxiv.org/pdf/2011.01507v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9f/70/9f70459f806445a8d62968e53a16f3f130aae558.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.01507v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Differentiable Fine-grained Quantization for Deep Neural Network Compression [article]

Hsin-Pai Cheng, Yuanjun Huang, Xuyang Guo, Yifei Huang, Feng Yan, Hai Li, Yiran Chen
<span title="2018-11-13">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a fine-grained quantization approach for deep neural network compression by relaxing the search space of quantization bitwidth from discrete to a continuous domain.  ...  Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted.  ...  To achieve this, we propose a fine-grained quantization approach that relaxes the search space of quantization bitwidth from discrete to continuous domain and applies gradient descend optimization to generate  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10351v3">arXiv:1810.10351v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sfbjws4turd7fi2izdvgoquxky">fatcat:sfbjws4turd7fi2izdvgoquxky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013213238/https://arxiv.org/pdf/1810.10351v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/66/77/6677d83ff877aa6522b9ab222703d5e22d01e688.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.10351v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification [article]

Krassimir Valev, Arne Schumann, Lars Sommer, Jürgen Beyerer
<span title="2018-06-08">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
task of fine-grained classification of vehicles.  ...  Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle.  ...  Fine-grained vehicle classification finds application in vehicle search and tracking, as well as traffic analysis.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.02987v1">arXiv:1806.02987v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eqqt2fvq5zfffcybigm2mjxyqy">fatcat:eqqt2fvq5zfffcybigm2mjxyqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824212406/https://arxiv.org/pdf/1806.02987v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e0/8d/e08dfe374538ee77bdb1c6a80053f66ca56ee618.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.02987v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Fine-Grained Image Similarity with Deep Ranking

Jiang Wang, Yang Song, Thomas Leung, Chuck Rosenberg, Jingbin Wang, James Philbin, Bo Chen, Ying Wu
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2014 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences.  ...  The deep ranking model employs a triplet-based hinge loss ranking function to characterize fine-grained image similarity relationships, and a multiscale neural network architecture to capture both the  ...  Search-by-example requires the distinction of differences between images within the same category, i.e., fine-grained image similarity.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2014.180">doi:10.1109/cvpr.2014.180</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WangSLRWPCW14.html">dblp:conf/cvpr/WangSLRWPCW14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mywmmpbizfelje2fbmmehqiyn4">fatcat:mywmmpbizfelje2fbmmehqiyn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20151129092502/http://users.eecs.northwestern.edu:80/~jwa368/pdfs/deep_ranking.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/4e/784e6bfd45ab1d79d350f72831c5c673e756482e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2014.180"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning Fine-grained Image Similarity with Deep Ranking [article]

Jiang Wang, Yang song, Thomas Leung, Chuck Rosenberg, Jinbin Wang, James Philbin, Bo Chen, Ying Wu
<span title="2014-04-17">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences.  ...  The deep ranking model employs a triplet-based hinge loss ranking function to characterize fine-grained image similarity relationships, and a multiscale neural network architecture to capture both the  ...  Search-by-example requires the distinction of differences between images within the same category, i.e., fine-grained image similarity.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1404.4661v1">arXiv:1404.4661v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uezz2kslnfajjmqziqj3t77uj4">fatcat:uezz2kslnfajjmqziqj3t77uj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901025422/https://arxiv.org/pdf/1404.4661v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ad/b8/adb88a77fafea86b17139565ac5600977af77198.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1404.4661v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Graph-RISE: Graph-Regularized Image Semantic Embedding [article]

Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, Sujith Ravi
<span title="2019-02-14">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
) ultra-fine-grained semantic labels.  ...  Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering.  ...  We refer to ultra fine-grained as "instance-level" to contrast with category-level and fine-grained semantics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.10814v1">arXiv:1902.10814v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m5a6vg7yz5g5bcayu3st7lua2m">fatcat:m5a6vg7yz5g5bcayu3st7lua2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191027100029/https://arxiv.org/pdf/1902.10814v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f8/83/f883427cda5d3b02f0087e48985e4d820d0d8038.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.10814v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution [article]

Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han
<span title="2020-08-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network  ...  With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes.  ...  Fig. 3 . 3 Overview of 3D Neural Architecture Search (3D-NAS): we first train a super network composed of multiple SPVConv's, supporting fine-grained channel numbers and elastic network depths.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.16100v2">arXiv:2007.16100v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/omt5fknvsndhlboulnvy6chh2i">fatcat:omt5fknvsndhlboulnvy6chh2i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200817190940/https://arxiv.org/pdf/2007.16100v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.16100v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search [article]

Yifan Jiang, Xinyu Gong, Junru Wu, Humphrey Shi, Zhicheng Yan, Zhangyang Wang
<span title="2021-12-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper bypasses existing 2D architectures, and directly searched for 3D architectures in a fine-grained space, where block type, filter number, expansion ratio and attention block are jointly searched  ...  A probabilistic neural architecture search method is adopted to efficiently search in such a large space.  ...  Neural architecture search (NAS) aims to replace the la- • A fine-grained design space for efficient video recogni- borious human design of network architectures, as well as tion is proposed, to  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04710v1">arXiv:2112.04710v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p3dxpblcx5f5xlohmas5odwu7e">fatcat:p3dxpblcx5f5xlohmas5odwu7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211211100912/https://arxiv.org/pdf/2112.04710v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0a/73/0a73ac5b75d7d991a07ebbdae9c904871d58dadc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04710v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 20,474 results