Web-Supervised Network with Softly Update-Drop Training for Fine-Grained Visual Classification

Zhang, Chuanyi; Yao, Yazhou; Liu, Huafeng; Xie, Guo-Sen; Shu, Xiangbo; Zhou, Tianfei; Zhang, Zheng; Shen, Fumin; Tang, Zhenmin

doi:10.1609/aaai.v34i07.6973

Cited by 49 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e mail system was originally designed to solve the problem of e-mail flooding and redundancy of a huge amount of information. And until the 21 st century, recommender systems were known as collaborative filtering systems [9]. In 1997, the journal ACM Communications, a division of the Association for Computing Machinery, organized the first special issue on collaborative filtering technology and used the term recommendation system as the title of the special issue, after which the term recommendation system became familiar.…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Visual Classification of Music Style Transfer Based on PSO‐BP Rating Prediction Model

2021

Complexity

View full text Add to dashboard Cite

In this paper, based on computer reading and processing of music frequency, amplitude, timbre, image pixel, color filling, and so forth, a method of image style transfer guided by music feature data is implemented in real-time playback, using existing music files and image files, processing and trying to reconstruct the fluent relationship between the two in terms of auditory and visual, generating dynamic, musical sound visualization with real-time changes in the visualization. Although recommendation systems have been well developed in real applications, the limitations of CF algorithms are slowly coming to light as the number of people increases day by day, such as the data sparsity problem caused by the scarcity of rated items, the cold start problem caused by new items and new users. The work is dynamic, with real-time changes in music and sound. Taking portraits as an experimental case, but allowing users to customize the input of both music and image files, this new visualization can provide users with a personalized service of mass customization and generate personalized portraits according to personal preferences. At the same time, we take advantage of the BP neural network’s ability to handle complex nonlinear problems and construct a rating prediction model between the user and item attribute features, referred to as the PSO-BP rating prediction model, by combining the features of global optimization of particle swarm optimization algorithm, and make further improvements based on the traditional collaborative filtering algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Visual Classification of Music Style Transfer Based on PSO‐BP Rating Prediction Model

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…In the Weakly Supervised Data Augmentation Network (WS-DAN) [24], high-quality features are kept and the useless features are dropped. Another direction to augment training set is through a Web-supervised network [29][30][31] that directly learns from the real-world Web images, which greatly increases the size of training set. A challenge with this approach is to eliminate irrelevant noisy images that are harmful to the training.…”

Section: Methods Using Data Augmentationmentioning

confidence: 99%

Learning Attention-Aware Interactive Features for Fine-Grained Vegetable and Fruit Classification

2021

View full text Add to dashboard Cite

Vegetable and fruit recognition can be considered as a fine-grained visual categorization (FGVC) task, which is challenging due to the large intraclass variances and small interclass variances. A mainstream direction to address the challenge is to exploit fine-grained local/global features to enhance the feature extraction and representation in the learning pipeline. However, unlike the human visual system, most of the existing FGVC methods only extract features from individual images during training. In contrast, human beings can learn discriminative features by comparing two different images. Inspired by this intuition, a recent FGVC method, named Attentive Pairwise Interaction Network (API-Net), takes as input an image pair for pairwise feature interaction and demonstrates superior performance in several open FGVC data sets. However, the accuracy of API-Net on VegFru, a domain-specific FGVC data set, is lower than expected, potentially due to the lack of spatialwise attention. Following this direction, we propose an FGVC framework named Attention-aware Interactive Features Network (AIF-Net) that refines the API-Net by integrating an attentive feature extractor into the backbone network. Specifically, we employ a region proposal network (RPN) to generate a collection of informative regions and apply a biattention module to learn global and local attentive feature maps, which are fused and fed into an interactive feature learning subnetwork. The novel neural structure is verified through extensive experiments and shows consistent performance improvement in comparison with the SOTA on the VegFru data set, demonstrating its superiority in fine-grained vegetable and fruit recognition. We also discover that a concatenation fusion operation applied in the feature extractor, along with three top-scoring regions suggested by an RPN, can effectively boost the performance.

show abstract

“…Sparse data has become the bottleneck of FGVC in both academic research and industrial applications. Recently, researchers' interests have shifted to saving expert effort during training, e.g., visual recognition with small-sample [25,26,47], websupervised learning [38,45], and leveraging layer persons annotations [10]. In this paper, we introduce a new lens to FGVC and propose a semi-supervised framework specifically aiming at FGVC tasks with out-of-distribution data.…”

Section: Fine-grained Visual Classificationmentioning

confidence: 99%

Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data

Du¹,

Chang²,

Ma³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for. Semi-supervised learning (SSL) techniques, acquiring knowledge from unlabeled data, provide a considerable means forward and have shown great promise for coarse-grained problems. However, exiting SSL paradigms mostly assume in-distribution (i.e., category-aligned) unlabeled data, which hinders their effectiveness when reproposed on FGVC. In this paper, we put forward a novel design specifically aimed at making out-of-distribution data work for semi-supervised FGVC, i.e., to "clue them in". We work off an important assumption that all fine-grained categories naturally follow a hierarchical structure (e.g., the phylogenetic tree of "Aves" that covers all bird species). It follows that, instead of operating on individual samples, we can instead predict sample relations within this tree structure as the optimization goal of SSL. Beyond this, we further introduced two strategies uniquely brought by these tree structures to achieve inter-sample consistency regularization and reliable pseudo-relation. Our experimental results reveal that (i) the proposed method yields good robustness against out-of-distribution data, and (ii) it can be equipped with prior arts, boosting their performance thus yielding state-of-the-art results. Code is available at https://github.com/PRIS-CV/RelMatch.

show abstract

Web-Supervised Network with Softly Update-Drop Training for Fine-Grained Visual Classification

Cited by 49 publications

References 22 publications

[Retracted] Visual Classification of Music Style Transfer Based on PSO‐BP Rating Prediction Model

[Retracted] Visual Classification of Music Style Transfer Based on PSO‐BP Rating Prediction Model

Learning Attention-Aware Interactive Features for Fine-Grained Vegetable and Fruit Classification

Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data

Contact Info

Product

Resources

About