paper-with-me

Papers

Rethinking Encoder-Decoder Flow Through Shared Structures

2025-01-24 · Frederik Laboyrie, Mehmet Kerim Yucel, Albert Saa-Garriga

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We introduce banks, shared structures that are used by each decoding block to provide additional context in the decoding process. These structures, through applying them via resampling and feature fusion, improve performance on depth estimation for state-of-the-art transformer-based architectures on natural and synthetic images whilst training on large-scale datasets.

📄 PDF Abstract BibTeX arXiv:2501.14535

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDepth Estimation

Similar Papers 제목 키워드 기반

Improving Domain Adaptation Translation with Domain Invariant and Specific Information

2019-04-08 · NAACL 2019 6 · Shuhao Gu, Yang Feng, Qun Liu

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model …

DecoderDomain AdaptationMachine TranslationTranslation

SENSE: a Shared Encoder Network for Scene-flow Estimation

2019-10-27 · ICCV 2019 10 · Huaizu Jiang, Deqing Sun, Varun Jampani, Zhaoyang Lv 외

We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion…

Disparity EstimationOcclusion EstimationOptical Flow EstimationScene Flow Estimation+1

Complexity Matters: Rethinking the Latent Space for Generative Modeling

2023-07-17 · NeurIPS 2023 11

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although…

Decoder

SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems

2026-07-14 · Yuxuan Ren, Fan Yang, Jianhua Yao, Yatao Bian arxiv

Small molecules, crystals, and proteins all reduce to atoms in 3D space, yet their generative pipelines remain fragmented across domains, each with its Small molecules, crystals, and proteins all reduce to atoms in 3D sp…

The Diffusion Encoder

2026-05-13 · Akhil Premkumar, Sarah Lucioni arxiv

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is m…