Liang-chieh Chen - Academia.edu (original) (raw)

Uploads

Papers by Liang-chieh Chen

Research paper thumbnail of The Devil is in the Decoder: Classification, Regression and GANs

International Journal of Computer Vision, 2019

Many machine vision applications, such as semantic segmentation and depth prediction, require pre... more 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 residuallike connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.

Research paper thumbnail of Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Labeling large-scale datasets with very accurate object segmentations is an elaborate task that r... more Labeling large-scale datasets with very accurate object segmentations is an elaborate task that requires a high degree of quality control and a budget of tens or hundreds of thousands of dollars. Thus, developing solutions that can automatically perform the labeling given only weak supervision is key to reduce this cost. In this paper, we show how to exploit 3D information to automatically generate very accurate object segmentations given annotated 3D bounding boxes. We formulate the problem as the one of inference in a binary Markov random field which exploits appearance models, stereo and/or noisy point clouds, a repository of 3D CAD models as well as topological constraints. We demonstrate the effectiveness of our approach in the context of autonomous driving, and show that we can segment cars with the accuracy of 86% intersection-over-union, performing as well as highly recommended MTurkers!

Research paper thumbnail of The Devil is in the Decoder: Classification, Regression and GANs

International Journal of Computer Vision, 2019

Many machine vision applications, such as semantic segmentation and depth prediction, require pre... more 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 residuallike connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.

Research paper thumbnail of Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Labeling large-scale datasets with very accurate object segmentations is an elaborate task that r... more Labeling large-scale datasets with very accurate object segmentations is an elaborate task that requires a high degree of quality control and a budget of tens or hundreds of thousands of dollars. Thus, developing solutions that can automatically perform the labeling given only weak supervision is key to reduce this cost. In this paper, we show how to exploit 3D information to automatically generate very accurate object segmentations given annotated 3D bounding boxes. We formulate the problem as the one of inference in a binary Markov random field which exploits appearance models, stereo and/or noisy point clouds, a repository of 3D CAD models as well as topological constraints. We demonstrate the effectiveness of our approach in the context of autonomous driving, and show that we can segment cars with the accuracy of 86% intersection-over-union, performing as well as highly recommended MTurkers!

Log In