Bin similarity‐based domain adaptation for fine‐grained image classification

Abstract

Fine‐grained classification tasks are challenging because fine‐grained data sets are quite scarce. Thus, we utilized the domain adaptation method to migrate knowledge from large, labeled data sets to fine‐grained target data sets. We employed the bin similarity (BS) algorithm to measure and select the approximate domains from large‐scale data sets to the fine‐grained target domains. Source domain feature space was divided into multiple bins and the features of the target domains were sampled to fill the bins. The most similar domains were selected based on the similarity statistics of the sample features. We implemented the BS algorithm combined with the popular convolutional neural networks, pretrained the network on the selected similar subdata sets, and subsequently fine‐tuned it on the fine‐grained data sets. We evaluated the BS classification model on Stanford Dogs and Oxford Flower data sets, and the results showed improved BS classification performance compared with the state‐of‐the‐art domain adaptation methods, earth mover's distance, selective joint fine‐tuning, L2 with starting point, and domain similarity for transfer learning. Furthermore, BS is a pluggable module that boosts the performance of domain adaptation.

Privacy‐preserving image retrieval in a distributed environment

“…Image processing involves a variety of different tasks, such as image retrieval, 7,8 image registration, 9 and even video retrieval 10 . Image retrieval is one of the most essential and prevalent tasks in image processing and is one of the crucial work during constructing smart services as shown in Figure 1.…”

Knowledge graph and behavior portrait of intelligent attack against path planning

“…The neural networks have inherent vulnerabilities. 4,5 They can be attacked by adversarial examples. 6 On the other hand, the sensors on unmanned vehicles are too complex [7][8][9][10][11][12][13] and they can be cheated by false signals.…”

“…However, the security problems of unmanned vehicles are more and more serious since it depends on AI systems, such as neural networks and relies on too many sensors. The neural networks have inherent vulnerabilities 4,5 . They can be attacked by adversarial examples 6 .…”

Boosting cross‐task adversarial attack with random blur

“…Deep neural networks (DNNs) have achieved superior performance in many applications. [1][2][3][4] However, recent works have shown that DNNs are vulnerable to adversarial examples, [5][6][7][8] that is, input images perturbed by imperceptible noise can lead to inaccurate predictions of DNNs. The existence of adversarial examples raises concerns in security-sensitive applications, for example, self-driving cars 9 and face recognition.…”

“…Deep neural networks (DNNs) have achieved superior performance in many applications 1–4 . However, recent works have shown that DNNs are vulnerable to adversarial examples, 5–8 that is, input images perturbed by imperceptible noise can lead to inaccurate predictions of DNNs.…”