paper-with-me

홈 › Papers

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

2021-07-29 · Jiali Duan, C. -C. Jay Kuo

The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long standing problem. The semantic gap problem is reviewed and a survey on recent efforts in bridging the gap is made in this work. Most importantly, we claim that the semantic gap is primarily bridged through supervised learning today. Experiences are drawn from two application domains to illustrate this point: 1) object detection and 2) metric learning for content-based image retrieval (CBIR). To begin with, this paper offers a historical retrospective on supervision, makes a gradual transition to the modern data-driven methodology and introduces commonly used datasets. Then, it summarizes various supervision methods to bridge the semantic gap in the context of object detection and metric learning.

📄 PDF Abstract BibTeX arXiv:2107.13757

Code (0)

등록된 구현이 없습니다.

Tasks

Content-Based Image RetrievalImage RetrievalMetric Learningobject-detectionObject DetectionRetrieval

Similar Papers 제목 키워드 기반

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation

2024-09-02 · Yunfei Xie, Cihang Xie, Alan Yuille, Jieru Mei

In this paper, we introduce a hierarchical transformer-based model designed for sophisticated image segmentation tasks, effectively bridging the granularity of part segmentation with the comprehensive scope of object seg…

Computational EfficiencyImage SegmentationObjectSegmentation+2

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

2023-09-24 · NeurIPS 2023 11 · Yun Xing, Jian Kang, Aoran Xiao, Jiahao Nie 외

Vision-Language Pre-training has demonstrated its remarkable zero-shot recognition ability and potential to learn generalizable visual representations from language supervision. Taking a step ahead, language-supervised s…

SegmentationSemantic SegmentationZero-Shot Learning

Changes-Aware Transformer: Learning Generalized Changes Representation

2023-09-24 · Dan Wang, Licheng Jiao, Jie Chen, Shuyuan Yang 외

Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit diverse changes, which may cause various…

Change Detection

Semantic Image Manipulation Using Scene Graphs

2020-04-07 · CVPR 2020 6 · Helisa Dhamo, Azade Farshad, Iro Laina, Nassir Navab 외

Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation have been, for the most part, tasks that op…

Image GenerationImage InpaintingImage ManipulationLayout-to-Image Generation

PixelSmile: Toward Fine-Grained Facial Expression Editing

2026-03-26 · Jiabin Hua, Hengyuan Xu, Aojie Li, Wei Cheng 외 arxiv

Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotations and establish FFE-B…

Contrastive Learning