paper-with-me

Papers

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

2022-04-21 · Chunbo Lang, Binfei Tu, Gong Cheng, Junwei Han

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the "episode" level, not just about the object cues themselves. Extensive experiments on PASCAL-5i and COCO-20i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5~10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.

📄 PDF Abstract BibTeX arXiv:2204.09903

Code (1)

chunbolang/DCP 공식 구현 pytorch

Tasks

DecoderFew-Shot Semantic SegmentationMeta-LearningSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Similar Papers 제목 키워드 기반

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking

2023-06-01 · Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan 외

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-l…

Dialogue State TrackingMixture-of-ExpertsTransfer Learning

FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions

2023-12-05 · Xu Shi, Wei Yao, Chuanchen Luo, Junran Peng 외

Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, generating motions beyond the…

Language ModelingLanguage ModellingLarge Language ModelMotion Generation

A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables

2026-05-11 · Zheng Li, Feng Xie, Shenglan Nie, Xichen Guo 외 arxiv

Constraint-based causal discovery is widely used for learning causal structures, but heavy reliance on conditional independence (CI) testing makes it computationally expensive in high-dimensional settings. To mitigate th…

Computational Efficiency

Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss and RKHS

2020-03-09 · Yong Liu, Lizhong Ding, Weiping Wang

Theoretical analysis of the divide-and-conquer based distributed learning with least square loss in the reproducing kernel Hilbert space (RKHS) have recently been explored within the framework of learning theory. However…

Learning Theory

Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach

2023-09-26 · Jian Xiao, Tianyuan Liu, Genlin Ji

Video anomaly detection is a complex task, and the principle of "divide and conquer" is often regarded as an effective approach to tackling intricate issues. It's noteworthy that recent methods in video anomaly detection…

Anomaly DetectionPhilosophyVideo Anomaly Detection