Learning Attentive Pairwise Interaction for Fine-Grained Classification

By Peiqin Zhuang, Yali Wang, Yu Qiao. AAAI Conference on Artificial Intelligence, 2020

407 citations recorded by the source corpus.

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e3ce51203b7763c9f3f20a62045578e562906d52

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “API-Net [111] was also built upon a metric learning framework, and can adaptively discover contrastive cues from a pair of images and distinguish them via pairwise attention based interactions.”
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification (2021, positive): “Notably, although a stronger backbone (DenseNet-161) is used in recent API-Net [70] method, our method can still achieve better performance on all three benchmarks.”
TransFG: A Transformer Architecture for Fine-grained Recognition (2021, methodology): “Our method outperforms most existing methods while performs worse than PMG [12] and API-Net [56] with small margin.”