paper-with-me

Papers

Region Semantically Aligned Network for Zero-Shot Learning

2021-10-14 · Ziyang Wang, Yunhao Gou, Jingjing Li, Yu Zhang, Yang Yang

Zero-shot learning (ZSL) aims to recognize unseen classes based on the knowledge of seen classes. Previous methods focused on learning direct embeddings from global features to the semantic space in hope of knowledge transfer from seen classes to unseen classes. However, an unseen class shares local visual features with a set of seen classes and leveraging global visual features makes the knowledge transfer ineffective. To tackle this problem, we propose a Region Semantically Aligned Network (RSAN), which maps local features of unseen classes to their semantic attributes. Instead of using global features which are obtained by an average pooling layer after an image encoder, we directly utilize the output of the image encoder which maintains local information of the image. Concretely, we obtain each attribute from a specific region of the output and exploit these attributes for recognition. As a result, the knowledge of seen classes can be successfully transferred to unseen classes in a region-bases manner. In addition, we regularize the image encoder through attribute regression with a semantic knowledge to extract robust and attribute-related visual features. Experiments on several standard ZSL datasets reveal the benefit of the proposed RSAN method, outperforming state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2110.07130

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeTransfer LearningZero-Shot Learning

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Similar Papers 제목 키워드 기반

Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval

2019-03-08 · CVPR 2019 6 · Anjan Dutta, Zeynep Akata

Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either r…

feature selectionImage RetrievalRetrievalSketch-Based Image Retrieval

Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs

2025-10-25 · Wei Xia arxiv

We proposed Static and Dynamic -- two zero-shot logits-layer debiasing methods. Dynamic reduces bias by up to 70% with minimal fluency loss. Logits intervention outperforms hidden-layer approaches. We show semantic-aware…

Semantically Aligned Bias Reducing Zero Shot Learning

2019-04-16 · CVPR 2019 6 · Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal

Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the …

Zero-Shot Learning

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval

2020-06-20 · Anjan Dutta, Zeynep Akata

Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase. Related prior works …

Generative Adversarial NetworkImage RetrievalRetrievalSketch-Based Image Retrieval

Context-Aware Zero-Shot Recognition

2019-04-19 · Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang

We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transf…

Object RecognitionZero-Shot Learning