Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Liu, Binghao; Ding, Yao; Jiao, J. B.; Ji, Xiangyang; Ye, Qixiang

doi:10.1109/cvpr46437.2021.00962

Cited by 40 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few-shot semantic segmentation is pioneered by Shaban et al [69]. Later works have mainly adopted the metricbased mainstream paradigm [18] with various improvements, e.g., improving the matching procedure between support-query images with various attention mechanisms [70,54,83], better optimizations [94,53], memory modules [77,79], graph neural networks [78,74,87], learning-based classifiers [72,59], progressive matching [32,96], or other advanced techniques [86,52,61,48]. We are the first to perform self-support matching between query prototype and query features.…”

Section: Related Workmentioning

confidence: 99%

Self-Support Few-Shot Semantic Segmentation

Fan¹,

Pei²,

Tai³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing few-shot segmentation methods have achieved great progress based on the support-query matching framework. But they still heavily suffer from the limited coverage of intra-class variations from the few-shot supports provided. Motivated by the simple Gestalt principle that pixels belonging to the same object are more similar than those to different objects of same class, we propose a novel self-support matching strategy to alleviate this problem, which uses query prototypes to match query features, where the query prototypes are collected from high-confidence query predictions. This strategy can effectively capture the consistent underlying characteristics of the query objects, and thus fittingly match query features. We also propose an adaptive self-support background prototype generation module and self-support loss to further facilitate the self-support matching procedure. Our self-support network substantially improves the prototype quality, benefits more improvement from stronger backbones and more supports, and achieves SOTA on multiple datasets. Codes are at https://github.com/fanq15/SSP.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-Support Few-Shot Semantic Segmentation

Fan¹,

Pei²,

Tai³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Chen et al [5] presents a baseline for few-shot classification that first pre-trains a backbone based on data from seen classes, and only finetunes the classifier for novel classes, which shares similarity with our decoupled training strategy. Apart from image classification, few-shot learning has also been applied to dense prediction tasks [6,21,23,53,54] and object detection [45].…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Incremental Learning with Continually Evolved Classifiers

Zhang¹,

Song²,

Lin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. Moreover, as training data come in sequence in FSCIL, the learned classifier can only provide discriminative information in individual sessions, while FSCIL requires all classes to be involved for evaluation. In this paper, we address the FSCIL problem from two aspects. First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations. By doing so, we demonstrate that a pre-trained backbone plus a nonparametric class mean classifier can beat state-of-the-art methods. Second, to make the classifiers learned on individual sessions applicable to all classes, we propose a Continually Evolved Classifier (CEC) that employs a graph model to propagate context information between classifiers for adaptation. To enable the learning of CEC, we design a pseudo incremental learning paradigm that episodically constructs a pseudo incremental learning task to optimize the graph parameters by sampling data from the base dataset. Experiments on three popular benchmark datasets, including CIFAR100, miniImageNet, and Caltech-USCD Birds-200-2011 (CUB200), show that our method significantly outperforms the baselines and sets new state-of-theart results with remarkable advantages.

show abstract

“…Existing few-shot learning methods can be broadly categorized as either: metric learning [23,21,5,34,33,14,15,11], meta-learning [28,17,3,7], or data augmentation [6,27]. Metric learning methods train networks to predict whether two images/regions belong to the same category.…”

Section: Few-shot Learningmentioning

confidence: 99%

Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection

Li¹,

Yang²,

Liu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Few-shot object detection has made substantial progress by representing novel class objects using the feature representation learned upon a set of base class objects. However, an implicit contradiction between novel class classification and representation is unfortunately ignored. On the one hand, to achieve accurate novel class classification, the distributions of either two base classes must be far away from each other (max-margin). On the other hand, to precisely represent novel classes, the distributions of base classes should be close to each other to reduce the intra-class distance of novel classes (min-margin). In this paper, we propose a class margin equilibrium (CME) approach, with the aim to optimize both feature space partition and novel class reconstruction in a systematic way. CME first converts the few-shot detection problem to the few-shot classification problem by using a fully connected layer to decouple localization features. CME then reserves adequate margin space for novel classes by introducing simple-yet-effective class margin loss during feature learning. Finally, CME pursues margin equilibrium by disturbing the features of novel class instances in an adversarial min-max fashion. Experiments on Pascal VOC and MS-COCO datasets show that CME significantly improves upon two baseline detectors (up to 3 ∼ 5% in average), achieving state-of-the-art performance. Code is available at https://github.com/Bohao-Lee/CME.

show abstract

Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Cited by 40 publications

References 23 publications

Self-Support Few-Shot Semantic Segmentation

Self-Support Few-Shot Semantic Segmentation

Few-Shot Incremental Learning with Continually Evolved Classifiers

Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection

Contact Info

Product

Resources

About