Latest Research
SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability.
Fast Sequence-Based Embedding with Diffusion Graphs
A graph embedding is a representation of graph vertices in a low-dimensional space, which approximately preserves properties such as distances between nodes.
Evaluating Weakly Supervised Object Localization Methods Right
In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
FEW-SHOT LEARNING MODEL SELECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting
Pairing stage calculates the error per sample, sorts the samples and pairs with strategy: hardest with easiest one, than mixing stage merges two samples using mixup, $x_1 + (1-\lambda)x_2$.
Correcting Knowledge Base Assertions
The usefulness and usability of knowledge bases (KBs) is often limited by quality issues.
Human-Aware Motion Deblurring
This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
CVPR 2019
• carrierlxk/COSNet
• 
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
SEMANTIC SEGMENTATION UNSUPERVISED VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION
Learning Compositional Neural Information Fusion for Human Parsing
The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively.
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION
Temporal Interlacing Network
In this way, a heavy temporal model is replaced by a simple interlacing operator.