Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

Sun, Xiaoxiao; Chen, Liyi; Yang, Jufeng

doi:10.1609/aaai.v33i01.3301273

Cited by 26 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

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

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

“…It has been widely applied to mitigate the distribution discrepancy between different domains (tasks). The essence of adversarial domain adaptation [9], [11], [14], [25]- [27] is to train a domain discriminator besides the feature extractor, and the two networks are optimized in an adversarial manner. The domain discriminator exerts to distinguish the source domain representations from the target domain ones, while the feature extractor, acting as the generator in typical GAN setting, tries to learn domain-invariant features by fooling the discriminator.…”

Section: B Adversarial Domain Adaptationmentioning

confidence: 99%

“…That is, making the distributions P (f s )={G f (x; θ f )|x ∼ P (X s )} and P (f t ) = {G f (x; θ f )|x ∼ P (X t )} to be aligned. We follow the idea of adversarial domain adaptation, as [11], [14], [25]- [27]. Specifically, we train a domain discriminator G d (parameterized with θ d ) along with the feature extractor G f in a min-max way.…”

Section: B Domain-level Alignmentmentioning

confidence: 99%

Learning Domain-Invariant Discriminative Features for Heterogeneous Face Recognition

Yang

Xiao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Heterogeneous face recognition (HFR), referring to matching face images across different domains, is a challenging problem due to the vast cross-domain discrepancy and insufficient pairwise cross-domain training data. This paper proposes a quadruplet framework for learning domain-invariant discriminative features (DIDF) for HFR, which integrates domain-level and class-level alignment in one unified network. The domain-level alignment reduces the cross-domain distribution discrepancy. The classlevel alignment based on a special quadruplet loss is developed to further diminish the intra-class variations and enlarge the inter-class separability among instances, thus handling the misalignment and adversarial equilibrium problems confronted by the domain-level alignment. With a bidirectional cross-domain data selection strategy, the quadruplet loss-based method prominently enriches the training set and further eliminates the cross-modality shift. Benefiting from the joint supervision and mutual reinforcement of these two components, the domain invariance and class discrimination of identity features are guaranteed. Extensive experiments on the challenging CASIA NIR-VIS 2.0 database, the Oulu-CASIA NIR&VIS database, the BUAA-VisNir database, and the IIIT-D viewed sketch database demonstrate the effectiveness and preferable generalization capability of the proposed method. INDEX TERMS adversarial domain adaptation, domain-invariant feature, heterogeneous face recognition, quadruplet loss

show abstract

Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

Cited by 26 publications

References 32 publications

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

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

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

Learning Domain-Invariant Discriminative Features for Heterogeneous Face Recognition

Contact Info

Product

Resources

About