# Densely connected multidilated convolutional networks for dense prediction tasks

arXiv: https://arxiv.org/abs/2011.11844 · HTML: https://mlsanity.com/paper/2011.11844/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2020.

## Built on by (most cited first, 21 of 21)

- [Multi-Task Learning with Multi-Query Transformer for Dense Prediction](https://mlsanity.com/paper/2205.14354/) (2022)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos](https://mlsanity.com/paper/2212.07065/) (2022)
- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)
- [Spider: A Unified Framework for Context-dependent Concept Segmentation](https://mlsanity.com/paper/2405.01002/) (2024)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)
- [Robust One-Shot Singing Voice Conversion](https://mlsanity.com/paper/2210.11096/) (2022)
- [Weakly-supervised Audio Separation via Bi-modal Semantic Similarity](https://mlsanity.com/paper/2404.01740/) (2024)
- [Points2Sound: From mono to binaural audio using 3D point cloud scenes](https://mlsanity.com/paper/2104.12462/) (2021)
- [Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention](https://mlsanity.com/paper/2207.02126/) (2022)
- [OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation](https://mlsanity.com/paper/2409.19270/) (2024)
- [What Makes Sound Event Localization and Detection Difficult? Insights from Error Analysis](https://mlsanity.com/paper/2107.10469/) (2021)
- [Improving Polyphonic Sound Event Detection on Multichannel Recordings with the Sorensen-Dice Coefficient Loss and Transfer Learning](https://mlsanity.com/paper/2107.10471/) (2021)
- [Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection](https://mlsanity.com/paper/2110.06126/) (2021)
- [Sampling-Frequency-Independent Universal Sound Separation](https://mlsanity.com/paper/2309.12581/) (2023)
- [Breaking the Context Bottleneck on Long Time Series Forecasting](https://mlsanity.com/paper/2412.16572/) (2024)
- [Text-Queried Audio Source Separation via Hierarchical Modeling](https://mlsanity.com/paper/2505.21025/) (2025)
- [TD3Net: A temporal densely connected multi-dilated convolutional network for lipreading](https://mlsanity.com/paper/2506.16073/) (2025)

## Abstract (arXiv)

Tasks that involve high-resolution dense prediction require a modeling of both local and global patterns in a large input field. Although the local and global structures often depend on each other and their simultaneous modeling is important, many convolutional neural network (CNN)-based approaches interchange representations in different resolutions only a few times. In this paper, we claim the importance of a dense simultaneous modeling of multiresolution representation and propose a novel CNN architecture called densely connected multidilated DenseNet (D3Net). D3Net involves a novel multidilated convolution that has different dilation factors in a single layer to model different resolutions simultaneously. By combining the multidilated convolution with the DenseNet architecture, D3Net incorporates multiresolution learning with an exponentially growing receptive field in almost all layers, while avoiding the aliasing problem that occurs when we naively incorporate the dilated convolution in DenseNet. Experiments on the image semantic segmentation task using Cityscapes and the audio source separation task using MUSDB18 show that the proposed method has superior performance over state-of-the-art methods.