Transfg: A transformer architecture for fine-grained recognition
Fine-grained visual classification (FGVC) which aims at recognizing objects from
subcategories is a very challenging task due to the inherently subtle inter-class differences …
subcategories is a very challenging task due to the inherently subtle inter-class differences …
Fine-grained visual classification via internal ensemble learning transformer
Recently, vision transformers (ViTs) have been investigated in fine-grained visual
recognition (FGVC) and are now considered state of the art. However, most ViT-based works …
recognition (FGVC) and are now considered state of the art. However, most ViT-based works …
Aa-trans: Core attention aggregating transformer with information entropy selector for fine-grained visual classification
The task of fine-grained visual classification (FGVC) is to distinguish targets from
subordinate classifications. Since fine-grained images have the inherent characteristic of …
subordinate classifications. Since fine-grained images have the inherent characteristic of …
Fine-grained predicates learning for scene graph generation
The performance of current Scene Graph Generation models is severely hampered by some
hard-to-distinguish predicates, eg," woman-on/standing on/walking on-beach" or" woman …
hard-to-distinguish predicates, eg," woman-on/standing on/walking on-beach" or" woman …
Fine-grained visual classification with high-temperature refinement and background suppression
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 …
categories and distinct differences among data within one single category. To address the …
A novel plug-in module for fine-grained visual classification
Visual classification can be divided into coarse-grained and fine-grained classification.
Coarse-grained classification represents categories with a large degree of dissimilarity, such …
Coarse-grained classification represents categories with a large degree of dissimilarity, such …
Adaptive fine-grained predicates learning for scene graph generation
The performance of current Scene Graph Generation (SGG) models is severely hampered
by hard-to-distinguish predicates, eg,“woman-on/standing on/walking on-beach”. As general …
by hard-to-distinguish predicates, eg,“woman-on/standing on/walking on-beach”. As general …
Mixture outlier exposure: Towards out-of-distribution detection in fine-grained environments
Many real-world scenarios in which DNN-based recognition systems are deployed have
inherently fine-grained attributes (eg, bird-species recognition, medical image classification) …
inherently fine-grained attributes (eg, bird-species recognition, medical image classification) …
Complemental attention multi-feature fusion network for fine-grained classification
Z Miao, X Zhao, J Wang, Y Li… - IEEE Signal Processing …, 2021 - ieeexplore.ieee.org
Transformer-based architecture network has shown excellent performance in the coarse-
grained image classification. However, it remains a challenge for the fine-grained image …
grained image classification. However, it remains a challenge for the fine-grained image …
The image data and backbone in weakly supervised fine-grained visual categorization: A revisit and further thinking
Weakly-supervised fine-grained visual categorization (FGVC) aims to achieve subclass
classification within the same large class using only label information. Compared to general …
classification within the same large class using only label information. Compared to general …