Diffpose: Toward more reliable 3d pose estimation
Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity
and occlusion, which often lead to high uncertainty and indeterminacy. On the other hand …
and occlusion, which often lead to high uncertainty and indeterminacy. On the other hand …
Few-shot image generation via adaptation-aware kernel modulation
Y Zhao, K Chandrasegaran… - Advances in …, 2022 - proceedings.neurips.cc
Few-shot image generation (FSIG) aims to learn to generate new and diverse samples given
an extremely limited number of samples from a domain, eg, 10 training samples. Recent …
an extremely limited number of samples from a domain, eg, 10 training samples. Recent …
Exploring incompatible knowledge transfer in few-shot image generation
Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from
a target domain using a few (eg, 10) reference samples. Existing FSIG methods select …
a target domain using a few (eg, 10) reference samples. Existing FSIG methods select …
Ecea: Extensible co-existing attention for few-shot object detection
Few-shot object detection (FSOD) identifies objects from extremely few annotated samples.
Most existing FSOD methods, recently, apply the two-stage learning paradigm, which …
Most existing FSOD methods, recently, apply the two-stage learning paradigm, which …
INSURE: an Information theory iNspired diSentanglement and pURification modEl for domain generalization
Domain Generalization (DG) aims to learn a generalizable model on the unseen target
domain by only training on the multiple observed source domains. Although a variety of DG …
domain by only training on the multiple observed source domains. Although a variety of DG …
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning
Existing Cross-Domain Few-Shot Learning (CDFSL) methods require access to source
domain data to train a model in the pre-training phase. However, due to increasing concerns …
domain data to train a model in the pre-training phase. However, due to increasing concerns …
Discriminative Feature Enhancement Network for few-shot classification and beyond
Few-shot classification aims to recognize query samples from novel classes given scarce
labeled data, which remains a challenging problem in machine learning. This paper …
labeled data, which remains a challenging problem in machine learning. This paper …
Embedding enhancement with foreground feature alignment and primitive knowledge for few-shot learning
X Zheng, J Lu - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Abstract Few-Shot Learning (FSL) targets a model to quickly discriminate new categories
with limited samples. While most methods struggle to effectively utilize the knowledge …
with limited samples. While most methods struggle to effectively utilize the knowledge …
Dual-model Collaborative Learning with Knowledge Clustering for Few-shot Image Classification
M Xiong, W Cao, Z Zhao - Multimedia Tools and Applications, 2024 - Springer
Few-shot learning (FSL) refers to adapt model to novel classes with few annotations.
Existing methods generally utilize a single model's information directly extracted from …
Existing methods generally utilize a single model's information directly extracted from …
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning
Learning invariant representations via contrastive learning has seen state-of-the-art
performance in domain generalization (DG). Despite such success, in this paper, we find …
performance in domain generalization (DG). Despite such success, in this paper, we find …