no code implementations • 25 May 2022 • Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw, Aleš Leonardis, Radu Timofte, Zexin Zhang, Cen Liu, Yunbo Peng, Yue Lin, Gaocheng Yu, Jin Zhang, Zhe Ma, Hongbin Wang, Xiangyu Chen, Xintao Wang, Haiwei Wu, Lin Liu, Chao Dong, Jiantao Zhou, Qingsen Yan, Song Zhang, Weiye Chen, Yuhang Liu, Zhen Zhang, Yanning Zhang, Javen Qinfeng Shi, Dong Gong, Dan Zhu, Mengdi Sun, Guannan Chen, Yang Hu, Haowei Li, Baozhu Zou, Zhen Liu, Wenjie Lin, Ting Jiang, Chengzhi Jiang, Xinpeng Li, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Juan Marín-Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Chunyang Li, Long Bao, Gang He, Ziyao Xu, Li Xu, Gen Zhan, Ming Sun, Xing Wen, Junlin Li, Shuang Feng, Fei Lei, Rui Liu, Junxiang Ruan, Tianhong Dai, Wei Li, Zhan Lu, Hengyan Liu, Peian Huang, Guangyu Ren, Yonglin Luo, Chang Liu, Qiang Tu, Fangya Li, Ruipeng Gang, Chenghua Li, Jinjing Li, Sai Ma, Chenming Liu, Yizhen Cao, Steven Tel, Barthelemy Heyrman, Dominique Ginhac, Chul Lee, Gahyeon Kim, Seonghyun Park, An Gia Vien, Truong Thanh Nhat Mai, Howoon Yoon, Tu Vo, Alexander Holston, Sheir Zaheer, Chan Y. Park
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
This minimizes the interference between parameters for different tasks.
This motivates us to propose a memory-augmented dynamic neural relational inference method, which maintains two associative memory pools: one for the interactive relations and the other for the individual entities.
Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection.
Due to the lack of supervision in the target domain, it is crucial to identify the underlying similarity-and-dissimilarity relationships among the unlabelled samples in the target domain.
Our insight is that the prediction target in SemSL can be modeled as the latent factor in the predictor for the SlfSL target.
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs.
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding.
Ranked #16 on 3D Instance Segmentation on ScanNet(v2)
Finally, we aggregate the global appearance and part features to improve the feature performance further.
To tackle the unsupervised domain adaptation problem, we explore the possibilities to generate high-quality labels as proxy labels to supervise the training on target data.
Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data.
To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride.
RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).
Ranked #18 on 3D Semantic Scene Completion on NYUv2
Then, we incorporate such a prior into inferring the joint posterior over network weights and the variance in the hierarchical prior, with which both the network training and the dropout rate estimation can be cast into a joint optimization problem.
In this paper, we propose a learning method to train diagnosis models, where our approach is designed to work with relatively small datasets.
Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization.
Existing sparsity-based priors are usually rooted in modeling the response of images to some specific filters (e. g., image gradients), which are insufficient to capture the complicated image structures.
Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.
Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process.
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
We show here that a subset of the image gradients are adequate to estimate the blur kernel robustly, no matter the gradient image is sparse or not.