In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of large-scale 3D datasets.
Ranked #2 on 3D Semantic Segmentation on ScanNet200 (using extra training data)
Although extensive research has been conducted on 3D point cloud segmentation, effectively adapting generic models to novel categories remains a formidable challenge.
In this work, we propose a new segmentation task -- reasoning segmentation.
We hope our work can benefit broader industrial applications where novel classes with limited annotations are required to be decently identified.
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and observe that it is equivalent to the Doupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels.
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations.
Ranked #6 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing.
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects.
Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
Ranked #5 on Long-tail Learning on iNaturalist 2018
Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg).
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations.
In this paper, we study the problem of class imbalance in semantic segmentation.
Ranked #21 on Semantic Segmentation on ADE20K
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them.
To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance.
In this work, we revisit the prior mask guidance proposed in ``Prior Guided Feature Enrichment Network for Few-Shot Segmentation''.
Semantic segmentation has made tremendous progress in recent years.
From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible.
Ranked #18 on Long-tail Learning on iNaturalist 2018
Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image.
It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks.
Ranked #63 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
Albeit intensively studied, false prediction and unclear boundaries are still major issues of salient object detection.
We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene.