Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Behera, Ardhendu; Wharton, Zachary; Hewage, Pradeep; Bera, Asish

doi:10.48550/arxiv.2101.06635

Cited by 5 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to Imagenet-1k, when we transfer networks trained on Imagenet-21k, MetaFormer-1 achieved 2.0% and 2.2% improvements on CUB-200-2011 and NABirds. The accuracy of CUB-200-2011 and NABirds is 92.3% and 92.7%, respectively, which outperforms the SotA approaches (91.8% and 91.0% on CAP [2]) by a clear margin, using iNaturalist 2021 for pre-training. iNaturalist 2021 with fewer data can perform better than Imagenet-21k since the domain similarity between iNaturalist 2021 and downstream datasets is higher.…”

Section: The Importance Of Pre-trained Modelmentioning

confidence: 94%

“…Note that these methods are verified based on the poor baseline. In addition, CAP [2] achieved the SotA performance on the CUB-200-2011. Our method can achieve comparable per-Table 4.…”

Section: The Power Of Meta Informationmentioning

confidence: 95%

“…DBTNet [54] proposed deep bilinear transformation, which takes advantage of semantic information and can obtain bilinear features efficiently. CAP [2] designed context-aware attentional pooling to captures subtle changes in image. TransFG [18] proposed a Part Selection Module to select discriminative image patches applying vision transformer.…”

Section: Fine-grained Visual Classificationmentioning

confidence: 99%

See 2 more Smart Citations

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

Diao¹,

Jiang²,

Wen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fine-Grained Visual Classification (FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple framework to utilize various meta-information to assist in fine-grained identification? To answer this problem, we explore a unified and strong meta-framework (MetaFormer) for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. Moreover, MetaFormer also provides a strong baseline for FGVC without bells and whistles. Extensive experiments demonstrate that MetaFormer can effectively use various metainformation to improve the performance of fine-grained recognition. In a fair comparison, MetaFormer can outperform the current SotA approaches with only vision information on the iNaturalist2017 and iNaturalist2018 datasets. Adding meta-information, MetaFormer can exceed the current SotA approaches by 5.9% and 5.3%, respectively. Moreover, MetaFormer can achieve 92.3% and 92.7% on CUB-200-2011 and NABirds, which significantly outperforms the SotA approaches. The source code and pretrained models are released at https://github.com/ dqshuai/MetaFormer.Recent advances in image classification [18,33] demonstrate large-scale pre-training could effectively improve the

show abstract

Section: The Importance Of Pre-trained Modelmentioning

confidence: 94%

“…Note that these methods are verified based on the poor baseline. In addition, CAP [2] achieved the SotA performance on the CUB-200-2011. Our method can achieve comparable per-Table 4.…”

Section: The Power Of Meta Informationmentioning

confidence: 95%

Section: Fine-grained Visual Classificationmentioning

confidence: 99%

See 1 more Smart Citation

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

Diao¹,

Jiang²,

Wen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To tackle above limitation, [9] exploits cosegmentation and alignment methods to generate discriminative regions aiming to learn which parts are vital to recognition. [10,11,12,13] researches on attention-based methods that just exploits image-level annotations to guide the deep network focusing on the most essential region with regard to each category. [11] designs a training paradigm that enables navigator to detect most informative regions via the teacher.…”

Section: Related Workmentioning

confidence: 99%

“…[12] explores the rich relationships between self-channels and interaction-channels which assists the network obtaining subtle inter-class difference. [13] adopts a context-aware attention pooling to capture subtle changes via sub-pixel gradients.…”

Section: Related Workmentioning

confidence: 99%

A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval

Zhao¹,

Wang²,

Lyu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Large-scale fine-grained image retrieval has two main problems. First, low dimensional feature embedding can fasten the retrieval process but bring accuracy reduce due to overlooking the feature of significant attention regions of images in fine-grained datasets. Second, fine-grained images lead to the same category query hash codes mapping into the different cluster in database hash latent space. To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.For the first issue, we propose an adaptive augmentation module in FCAENet, which is selective region erasing module (SREM). SREM makes the network more robust on subtle differences of fine-grained task by adaptively covering some regions of raw images. The feature extractor and hash layer can learn more representative hash code for fine-grained images by SREM. With regard to the second issue, we fully exploit the pair-wise similarity information and add the enhancing space relation loss (ESRL) in FCAENet to make the vulnerable relation stabler between the query hash code and database hash code. We conduct extensive experiments on five fine-grained benchmark datasets (CUB2011, Aircraft, NABirds, VegFru, Food101) for 12bits, 24bits, 32bits, 48bits hash code. The results show that FCAENet achieves the state-of-the-art (SOTA) fine-grained retrieval performance compared with other methods.

show abstract

A survey: researches advanced in weakly supervised fine-grained visual classification

Ran

2022

2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022)

View full text Add to dashboard Cite

With the development of multimedia technology, Fine-Grained Visual Classification (FGVC) has gradually become one of the new hot tasks in computer vision community, whose goal is to identify images that belong to the same species. Though the accuracy of FGVC has made a great breakthrough, the performance is still limited by the issue of locating objects’ discriminative regions, as common state-of-the-art convolutional neural networks that perform excellently in image classification task such as ImageNet-1k cannot be directly applied to FGVC tasks. In this case, we provide a comprehensive and systematic survey of recent advances in FGVC field and divide the existing methods into: creative application of attentive structures, aids of diverse pretraining methods, various designs of loss functions and other innovative methods. We further analyze the performance of representative methods on common data sets, and finally summarize the existing problems in the FGVC research field and predict the solutions to these problems in the future.

show abstract

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Cited by 5 publications

References 0 publications

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval

A survey: researches advanced in weakly supervised fine-grained visual classification

Contact Info

Product

Resources

About