Fine-grained Visual Classification with High-temperature Refinement and Background Suppression Article Swipe

MAKE IMPACT

Po‐Yung Chou , Yu-Yung Kao , Cheng‐Hung Lin · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2303.06442

Fine-grained visual classification is a challenging task due to the high similarity between categories and distinct differences among data within one single category. To address the challenges, previous strategies have focused on localizing subtle discrepancies between categories and enhencing the discriminative features in them. However, the background also provides important information that can tell the model which features are unnecessary or even harmful for classification, and models that rely too heavily on subtle features may overlook global features and contextual information. In this paper, we propose a novel network called ``High-temperaturE Refinement and Background Suppression'' (HERBS), which consists of two modules, namely, the high-temperature refinement module and the background suppression module, for extracting discriminative features and suppressing background noise, respectively. The high-temperature refinement module allows the model to learn the appropriate feature scales by refining the features map at different scales and improving the learning of diverse features. And, the background suppression module first splits the features map into foreground and background using classification confidence scores and suppresses feature values in low-confidence areas while enhancing discriminative features. The experimental results show that the proposed HERBS effectively fuses features of varying scales, suppresses background noise, discriminative features at appropriate scales for fine-grained visual classification.The proposed method achieves state-of-the-art performance on the CUB-200-2011 and NABirds benchmarks, surpassing 93% accuracy on both datasets. Thus, HERBS presents a promising solution for improving the performance of fine-grained visual classification tasks. code: https://github.com/chou141253/FGVC-HERBS

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2303.06442

PDF

https://arxiv.org/pdf/2303.06442

OA Status

green

Cited By

29

Related Works

10

OpenAlex ID

https://openalex.org/W4324314567

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4324314567

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2303.06442

Digital Object Identifier

Title

Fine-grained Visual Classification with High-temperature Refinement and Background Suppression

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-03-11

Full publication date if available

Authors

Po‐Yung Chou, Yu-Yung Kao, Cheng‐Hung Lin

List of authors in order

Landing page

https://arxiv.org/abs/2303.06442

Publisher landing page

PDF URL

https://arxiv.org/pdf/2303.06442

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2303.06442

Direct OA link when available

Concepts

Discriminative model, Computer science, Artificial intelligence, Feature (linguistics), Pattern recognition (psychology), Similarity (geometry), Noise (video), Task (project management), Code (set theory), Machine learning, Image (mathematics), Set (abstract data type), Philosophy, Programming language, Economics, Management, Linguistics

Top concepts (fields/topics) attached by OpenAlex

Cited by

29

Total citation count in OpenAlex

Citations by year (recent)

2025: 8, 2024: 17, 2023: 4

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload