Irremediable
发表于 2025-3-30 11:17:51
,Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation,a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into
连接
发表于 2025-3-30 14:05:33
http://reply.papertrans.cn/24/2343/234275/234275_52.png
Keshan-disease
发表于 2025-3-30 18:49:04
,CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition,n seen classes which generalizes well to instances of unseen classes, without losing discriminability between classes. Neural networks are able to model highly complex boundaries between visual classes, which explains their success as supervised models. However, in Zero-Shot learning, these highly s
bourgeois
发表于 2025-3-30 21:50:30
http://reply.papertrans.cn/24/2343/234275/234275_54.png
拍翅
发表于 2025-3-31 04:26:19
http://reply.papertrans.cn/24/2343/234275/234275_55.png
MIRE
发表于 2025-3-31 07:45:24
,DnA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment,ver, when transferring such representations to downstream tasks with domain shifts, the performance degrades compared to its supervised counterpart, especially at the few-shot regime. In this paper, we proposed to boost the transferability of the self-supervised pre-trained models on cross-domain ta
宇宙你
发表于 2025-3-31 10:27:13
,Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning,le way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task. Dynamic networks have been shown capable of learning content-adaptive parameters efficiently, making them suitable for few-shot learning. In this paper, we propose to learn the dynamic
forecast
发表于 2025-3-31 17:05:59
,Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding,cent zero-shot segmentation attracts a lot of attention by exploring the relationships between unseen and seen object categories, yet requiring large amounts of densely-annotated data with diverse base classes. In this paper, we propose a new open-world semantic segmentation pipeline that makes the
RAFF
发表于 2025-3-31 18:30:21
http://reply.papertrans.cn/24/2343/234275/234275_59.png
Accrue
发表于 2025-3-31 21:52:07
,Time-rEversed DiffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection,ult in information loss; and/or (ii) discard position information that can help detect object instances. Consequently, such pipelines are sensitive to large intra-class appearance and geometric variations between support and query images. To address these drawbacks, we propose a Time-rEversed diffus