Search Results for author:
Found 10 papers, 7 papers with code
Weight-guided class complementing for long-tailed image recognition
In this paper, we propose a Weight-Guided Class Complementing framework to address this issue.
Ranked #11 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions within feature clusters defined by label and pseudo labels.
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection
To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects.
Ranked #3 on
Co-Salient Object Detection
on CoCA
Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation
In this paper, we propose a new regularized loss which utilizes both shallow and deep features that are dynamically updated in order to aggregate sufficient information to represent the relationship of different pixels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Fast Pixel-Matching for Video Object Segmentation
Most mask-propagation based models are faster but with relatively low performance due to failure to adapt to object appearance variation.
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset.
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
Specifically, through making an initial prediction for the annotated support image, the covered and uncovered foreground regions are encoded to the primary and auxiliary support vectors using masked GAP, respectively.
Ranked #62 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence
Since scribble labels fail to offer detailed salient regions, we propose a local coherence loss to propagate the labels to unlabeled regions based on image features and pixel distance, so as to predict integral salient regions with complete object structures.
Fast Template Matching and Update for Video Object Tracking and Segmentation
Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result.
Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach
Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization.
Ranked #22 on
Semantic Segmentation
on PASCAL VOC 2012 val
