Learning to Navigate for Fine-grained Classification

By Ze Yang, Tiange Luo, Jun Gao, Liwei Wang. European Conference on Computer Vision, 2018

490 citations recorded by the source corpus.

Fine-grained classification is challenging due to the difficulty of finding discriminative features. Finding those subtle traits that fully characterize the object is not straightforward. To handle this circumstance, we propose a novel self-supervision mechanism to effectively localize informative regions without the need of bounding-box/part annotations. Our model, termed NTS-Net for Navigator-Teacher-Scrutinizer Network, consists of a Navigator agent, a Teacher agent and a Scrutinizer agent. In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher. After that, the Scrutinizer scrutinizes the proposed regions from Navigator and makes predictions. Our model can be viewed as a multi-agent cooperation, wherein agents benefit from each other, and make progress together. NTS-Net can be trained end-to-end, while provides accurate fine-grained classification predictions as well as highly informative regions during inference. We achieve state-of-the-art performance in extensive benchmark datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/472e4265895de65961b70779fdfbecafc24079ed

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

Transductive Learning for Zero-Shot Object Detection (2019, background): “As a result, deep CNNs are now performing as well as humans on specialized tasks of visual recognition and fine-grained categorization [17, 33].”
Learning Attentive Pairwise Interaction for Fine-Grained Classification (2020, background): “2017)), learning a bank of discriminative filters (Wang, Morariu, and Davis 2018), guiding region detection with multi-agent cooperation (Yang et al. 2018), etc.”
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (2020, background): “[46] proposed a novel multi-agent cooperative learning scheme which learns to identify the discriminative regions in the image in a self-supervised way.”
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (2020, methodology): “prediction [38,11,12,35].”
Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition (2019, background): “Moreover, although NTSN [37] (K = 2) concatenates global feature with two part features, our singlestream TASN still can achieve 0.”
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification (2021, unknown): “0 NTS-Net [63] 87.”
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization (2020, methodology): “Other methods [8,9,10,11] use an unsupervised learning scheme to localize informative regions.”
TransFG: A Transformer Architecture for Fine-grained Recognition (2021, background): “NTS-Net [49] exploits ranking loss to maintain a consistency for learning region features which ignored the global relationship.”
See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification (2019, unknown): “4 NTS-Net [33] 87.”
Destruction and Construction Learning for Fine-Grained Image Recognition (2019, methodology): “[35] introduced a method to detect informative regions and then scrutinizes them to make final predictions.”
Deep Learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) With CT Images (2020, methodology): “Based on FPN, our model can not only provide person-level prediction score for the doctor but also interpret the prediction by weighing each pixel of the original image.”
Relational Knowledge Distillation (2019, methodology): “For such datasets, effective adaptation to specific characteristics of the domain may be crucial; recent methods for fine-grained classification focus on localizing discriminative parts of target-domain objects [23, 44, 48].”
Multi-attentional Deepfake Detection (2021, background): “Fine-grained classification [50, 49, 13, 37, 12, 52, 47, 17, 10] is a challenging research task in computer vision, which captures the local discriminative features to distinguish different fine-grained categories.”
Differentiable Patch Selection for Image Recognition (2021, methodology): “Numbers for prior work were taken from Table 2 of [47].”