Search Results for author: Siyang Li

Found 10 papers, 2 papers with code

The surprising impact of mask-head architecture on novel class segmentation

3 code implementations ICCV 2021 Vighnesh Birodkar, Zhichao Lu, Siyang Li, Vivek Rathod, Jonathan Huang

Under this family, we study Mask R-CNN and discover that instead of its default strategy of training the mask-head with a combination of proposals and groundtruth boxes, training the mask-head with only groundtruth boxes dramatically improves its performance on novel classes.

Instance Segmentation Semantic Segmentation

Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages

no code implementations24 Mar 2021 Garry Kuwanto, Afra Feyza Akyürek, Isidora Chara Tourni, Siyang Li, Alexander Gregory Jones, Derry Wijaya

We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages.

Cross-Lingual Bitext Mining Language Modelling +2

Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation

no code implementations19 Dec 2018 Ye Wang, Jongmoo Choi, Yueru Chen, Siyang Li, Qin Huang, Kaitai Zhang, Ming-Sui Lee, C. -C. Jay Kuo

Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.

Frame Instance Segmentation +3

Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation

no code implementations13 Dec 2018 Ye Wang, Jongmoo Choi, Yueru Chen, Qin Huang, Siyang Li, Ming-Sui Lee, C. -C. Jay Kuo

Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.

Instance Segmentation Object Tracking +3

Interpretable Convolutional Neural Networks via Feedforward Design

2 code implementations5 Oct 2018 C. -C. Jay Kuo, Min Zhang, Siyang Li, Jiali Duan, Yueru Chen

To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform.

Unsupervised Video Object Segmentation with Motion-based Bilateral Networks

no code implementations ECCV 2018 Siyang Li, Bryan Seybold, Alexey Vorobyov, Xuejing Lei, C. -C. Jay Kuo

First, we propose a motion-based bilateral network to estimate the background based on the motion pattern of non-object regions.

Ranked #2 on Video Object Segmentation on DAVIS 2016 (Average MAE metric)

Frame Semantic Segmentation +3

Instance Embedding Transfer to Unsupervised Video Object Segmentation

no code implementations CVPR 2018 Siyang Li, Bryan Seybold, Alexey Vorobyov, Alireza Fathi, Qin Huang, C. -C. Jay Kuo

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks.

Optical Flow Estimation Semantic Segmentation +2

Multiple Instance Curriculum Learning for Weakly Supervised Object Detection

no code implementations25 Nov 2017 Siyang Li, Xiangxin Zhu, Qin Huang, Hao Xu, C. -C. Jay Kuo

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e. g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects.

Multiple Instance Learning Semantic Segmentation +1

A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision

no code implementations3 Nov 2017 Chi-Hao Wu, Qin Huang, Siyang Li, C. -C. Jay Kuo

Being inspired by child's learning experience - taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work.

Object Detection

Semantic Segmentation with Reverse Attention

no code implementations20 Jul 2017 Qin Huang, Chunyang Xia, Chi-Hao Wu, Siyang Li, Ye Wang, Yuhang Song, C. -C. Jay Kuo

Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.