paper-with-me

홈 › Papers

Local Propagation for Few-Shot Learning

2021-01-05 · Yann Lifchitz, Yannis Avrithis, Sylvaine Picard

The challenge in few-shot learning is that available data is not enough to capture the underlying distribution. To mitigate this, two emerging directions are (a) using local image representations, essentially multiplying the amount of data by a constant factor, and (b) using more unlabeled data, for instance by transductive inference, jointly on a number of queries. In this work, we bring these two ideas together, introducing \emph{local propagation}. We treat local image features as independent examples, we build a graph on them and we use it to propagate both the features themselves and the labels, known and unknown. Interestingly, since there is a number of features per image, even a single query gives rise to transductive inference. As a result, we provide a universally safe choice for few-shot inference under both non-transductive and transductive settings, improving accuracy over corresponding methods. This is in contrast to existing solutions, where one needs to choose the method depending on the quantity of available data.

📄 PDF Abstract BibTeX arXiv:2101.01480

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos

2025-11-25 · Youngseo Kim, Dohyun Kim, Geonhee Han, Paul Hongsuck Seo arxiv

Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond synthesis. In this work, we investigate …

Video Object SegmentationImage GenerationObject Tracking

Segment Anything Meets Point Tracking

2023-07-03 · Frano Rajič, Lei Ke, Yu-Wing Tai, Chi-Keung Tang 외

The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both…

Interactive Video Object SegmentationObjectPoint TrackingSegmentation+4

Zero-Shot Temporal Action Detection via Vision-Language Prompting

2022-07-17 · Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

Existing temporal action detection (TAD) methods rely on large training data including segment-level annotations, limited to recognizing previously seen classes alone during inference. Collecting and annotating a large t…

Action DetectionClassificationimage-classificationImage Classification+2

PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning

2026-09-04 · Ruizhe Huang, Chengran Li, Xiaochuan Shi arxiv

Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override r…

Graph Learning

Adaptive Anchor Label Propagation for Transductive Few-Shot Learning

2023-10-30 · Michalis Lazarou, Yannis Avrithis, Guangyu Ren, Tania Stathaki

Few-shot learning addresses the issue of classifying images using limited labeled data. Exploiting unlabeled data through the use of transductive inference methods such as label propagation has been shown to improve the …

Few-Shot Learning