paper-with-me

홈 › Papers

Learning Semantically Enhanced Feature for Fine-Grained Image Classification

2020-06-24 · Wei Luo, Hengmin Zhang, Jun Li, Xiu-Shen Wei

We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter. Unlike previous methods that rely on complex part localization modules, our approach learns fine-grained features by enhancing the semantics of sub-features of a global feature. Specifically, we first achieve the sub-feature semantic by arranging feature channels of a CNN into different groups through channel permutation. Meanwhile, to enhance the discriminability of sub-features, the groups are guided to be activated on object parts with strong discriminability by a weighted combination regularization. Our approach is parameter parsimonious and can be easily integrated into the backbone model as a plug-and-play module for end-to-end training with only image-level supervision. Experiments verified the effectiveness of our approach and validated its comparable performance to the state-of-the-art methods. Code is available at https://github.com/cswluo/SEF

📄 PDF Abstract BibTeX arXiv:2006.13457

Code (2)

cswluo/SEF 공식 구현 pytorch
YNCao/mysef pytorch

Tasks

ClassificationFine-Grained Image ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention

2025-11-15 · Peng Zhang, Zhihui Lai, Wenting Chen, Xu Wu 외 arxiv

Medical vision-language pre-training (VLP) offers significant potential for advancing medical image understanding by leveraging paired image-report data. However, existing methods are limited by Fa}lse Negatives (FaNe) i…

Semantic SegmentationImage ClassificationObject Detection

Beyond Frequency: Seeing Subtle Cues Through the Lens of Spatial Decomposition for Fine-Grained Visual Classification

2025-08-09 · Qin Xu, Lili Zhu, Xiaoxia Cheng, Bo Jiang arxiv

The crux of resolving fine-grained visual classification (FGVC) lies in capturing discriminative and class-specific cues that correspond to subtle visual characteristics. Recently, frequency decomposition/transform based…

Fine-Grained Image Classification

CADFormer: Fine-Grained Cross-modal Alignment and Decoding Transformer for Referring Remote Sensing Image Segmentation

2025-03-30 · Maofu Liu, Xin Jiang, Xiaokang Zhang

Referring Remote Sensing Image Segmentation (RRSIS) is a challenging task, aiming to segment specific target objects in remote sensing (RS) images based on a given language expression. Existing RRSIS methods typically em…

cross-modal alignmentImage SegmentationSemantic Segmentation

Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification

2022-07-02 · Bo Zhang, Jiakang Yuan, Baopu Li, Tao Chen 외

Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences. Although learning different objects' local differences via Deep Neural Networks has ach…

Fine-Grained Image Classificationimage-classificationImage ClassificationObject+1

DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks

2024-09-10 · Amin Karimi Monsefi, Kishore Prakash Sailaja, Ali Alilooee, Ser-Nam Lim 외

In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like s…

Contrastive LearningImage ReconstructionLanguage ModelingLanguage Modelling+2