Hierarchical Feature Fusion

Introduced by Mehta et al. in ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Hierarchical Feature Fusion (HFF) is a feature fusion method employed in ESP and EESP image model blocks for degridding. In the ESP module, concatenating the outputs of dilated convolutions gives the ESP module a large effective receptive field, but it introduces unwanted checkerboard or gridding artifacts. To address the gridding artifact in ESP, the feature maps obtained using kernels of different dilation rates are hierarchically added before concatenating them (HFF). This solution is simple and effective and does not increase the complexity of the ESP module.

Source: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Latest Papers

PAPER DATE
A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline
Yerbolat KhassanovSaida MussakhojayevaAlmas MirzakhmetovAlen AdiyevMukhamet NurpeiissovHuseyin Atakan Varol
2020-09-22
Frame-To-Frame Consistent Semantic Segmentation
Manuel RebolPatrick Knöbelreiter
2020-08-03
ClueMeIn: Obtaining More Specific Image Labels Through a Game
Christopher Harris
2020-05-01
Do You Believe It Happened? Assessing Chinese Readers' Veridicality Judgments
Yu-Yun ChangShu-Kai Hsieh
2020-05-01
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Olivier FranconSantiago GonzalezBabak HodjatElliot MeyersonRisto MiikkulainenXin QiuHormoz Shahrzad
2020-02-13
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
| Tomoki HayashiRyuichi YamamotoKatsuki InoueTakenori YoshimuraShinji WatanabeTomoki TodaKazuya TakedaYu ZhangXu Tan
2019-10-24
Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Murali Karthick BaskarShinji WatanabeRamon AstudilloTakaaki HoriLukáš BurgetJan Černocký
2019-04-30
Differentiable reservoir computing
Lyudmila GrigoryevaJuan-Pablo Ortega
2019-02-16
C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation
| Hyojin ParkYoungjoon YooGeonseok SeoDongyoon HanSangdoo YunNojun Kwak
2018-12-12
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
| Sachin MehtaMohammad RastegariLinda ShapiroHannaneh Hajishirzi
2018-11-28
Chasing the Echo State Property
Claudio Gallicchio
2018-11-27
HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection
Pingping ZhangHuchuan LuChunhua Shen
2018-04-14
ESPnet: End-to-End Speech Processing Toolkit
Shinji WatanabeTakaaki HoriShigeki KaritaTomoki HayashiJiro NishitobaYuya UnnoNelson Enrique Yalta SoplinJahn HeymannMatthew WiesnerNanxin ChenAdithya RenduchintalaTsubasa Ochiai
2018-03-30
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
| Sachin MehtaMohammad RastegariAnat CaspiLinda ShapiroHannaneh Hajishirzi
2018-03-19

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories