paper-with-me

홈 › Papers

The Devil is in the Decoder: Classification, Regression and GANs

2017-07-18 · Zbigniew Wojna, Vittorio Ferrari, Sergio Guadarrama, Nathan Silberman, Liang-Chieh Chen, Alireza Fathi, Jasper Uijlings

Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. This paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise tasks ranging from classification, regression to synthesis. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce new residual-like connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.

📄 PDF Abstract BibTeX arXiv:1707.05847

Code (1)

bayraktarbaris/SNGAN pytorch

Tasks

Boundary DetectionDecoderDepth EstimationDepth PredictionGeneral ClassificationregressionSemantic Segmentation

Similar Papers 제목 키워드 기반

Fuzzy Generative Adversarial Networks

2021-10-27 · Ryan Nguyen, Shubhendu Kumar Singh, Rahul Rai

Generative Adversarial Networks (GANs) are well-known tools for data generation and semi-supervised classification. GANs, with less labeled data, outperform Deep Neural Networks (DNNs) and Convolutional Neural Networks (…

regression

Generalizing semi-supervised generative adversarial networks to regression using feature contrasting

2018-11-27 · Greg Olmschenk, Zhigang Zhu, Hao Tang

In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks u…

Age EstimationCrowd CountingGeneral Classificationregression

Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding

2025-12-07 · Shida Gao, Feng Xue, Xiangfeng Wang, Anlong Ming 외 arxiv

Multimodal large language models (MLLMs) are rapidly expanding from general video understanding to finer-grained understanding such as spatio-temporal video grounding (STVG) and reasoning. In these tasks, an MLLM must lo…

Spatio-Temporal Video Grounding

Propeller Motion of a Devil-Stick using Normal Forcing

2025-01-29 · Aakash Khandelwal, Ranjan Mukherjee

The problem of realizing rotary propeller motion of a devil-stick in the vertical plane using forces purely normal to the stick is considered. This problem represents a nonprehensile manipulation task of an underactuated…

AgeFlow: Conditional Age Progression and Regression with Normalizing Flows

2021-05-15 · Zhizhong Huang, Shouzhen Chen, Junping Zhang, Hongming Shan

Age progression and regression aim to synthesize photorealistic appearance of a given face image with aging and rejuvenation effects, respectively. Existing generative adversarial networks (GANs) based methods suffer fro…

AttributeKnowledge Distillationregression