paper-with-me

Papers

Free-Grained Hierarchical Visual Recognition

2025-10-16 · Seulki Park, Zilin Wang, Stella X. Yu arxiv

Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path. Reality is messier: A distant bird may be labeled only bird, while a clear close-up may justify bald eagle. We introduce free-grain training, where labels may appear at any level of the taxonomy and models must learn consistent hierarchical predictions from incomplete, mixed-granularity supervision. We build benchmark datasets with varying label granularity and show that existing hierarchical methods deteriorate sharply in this setting. To make up for missing supervision, we propose two simple solutions: One adds broad text-based supervision that captures visual attributes, and the other treats missing labels at specific taxonomy levels as a semi-supervised learning problem. We also study free-grained inference, where the model chooses how deep to predict, returning a reliable coarse label when a fine-grained one is uncertain. Together, our task, datasets, and methods move hierarchical recognition closer to the way labels arise in the real world.

📄 PDF Abstract BibTeX arXiv:2510.14737

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition

2018-07-26 · ECCV 2018 9 · Chaojian Yu, Xinyi Zhao, Qi Zheng, Peng Zhang 외

Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning. Bilinear pooling based models have been shown to be effective at fine-g…

Fine-Grained Visual Recognition

Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions

2025-05-29 · Jinyi Chang, Dongliang Chang, Lei Chen, Bingyao Yu 외

In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level labels, making the…

ClassificationDictionary LearningFine-Grained Image ClassificationMedical Image Analysis+1

Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context

2024-10-28 · Manuel Benavent-Lledo, David Mulero-Pérez, David Ortiz-Perez, Jose Garcia-Rodriguez 외

The sequential execution of actions and their hierarchical structure consisting of different levels of abstraction, provide features that remain unexplored in the task of action recognition. In this study, we present a n…

Action RecognitionFine-grained Action RecognitionOptical Flow Estimation

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

2020-06-16 · CVPR 2020 6 · Zongyan Han, Zhen-Yong Fu, Jian Yang

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of different …

Generalized Zero-Shot LearningObjectObject RecognitionZero-Shot Learning

From Coarse to Fine-Grained Open-Set Recognition

2024-01-01 · CVPR 2024 1 · Nico Lang, Vésteinn Snæbjarnarson, Elijah Cole, Oisin Mac Aodha 외

Open-set recognition (OSR) methods aim to identify whether or not a test example belongs to a category ob- served during training. Depending on how visually sim- ilar a test example is to the training categories the …

Fine-Grained Visual CategorizationOpen Set Learning