Finally, we use the matting module which takes the image, trimap and context features to estimate the alpha matte.
Ranked #1 on Image Matting on Composition-1K (using extra training data)
In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.
A practical long-term tracker typically contains three key properties, i. e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism.
RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked.
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
Unsupervised domain adaptation has attracted growing research attention on semantic segmentation.
Most of the existing trackers usually rely on either a multi-scale searching scheme or pre-defined anchor boxes to accurately estimate the scale and aspect ratio of a target.
To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts.
Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e. g., knowledge library or deep network weights.
We fully exploit the hierarchical features from all the convolutional layers.
To solve these problems, we propose the very deep residual channel attention networks (RCAN).
Ranked #10 on Image Super-Resolution on BSD100 - 4x upscaling
To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS).
In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers.
Ranked #1 on Color Image Denoising on CBSD68 sigma50
In this paper, an effective unconstrained correlation filter called Uncon- strained Optimal Origin Tradeoff Filter (UOOTF) is presented and applied to robust face recognition.
A hierarchical shape parsing strategy is proposed to partition and organize image components into a hierarchical structure in the scale space.