Convolutional Neural Network Copy Detection with Neural Network Perceptual Hashing

In recent years, many model intellectual property (IP) proof methods for IP protection have been proposed, such as model watermarking and model fingerprinting. However, as an important part of the model IP protection system, the model copy detection task has not received enough attention. With the increasing number of neural network models transmitted and deployed on the Internet, the search for similar models is in great demand, which concurrently triggers the security problem of copy detection of models for IP protection. Due to the high computational complexity, both model watermarking and model fingerprinting lack the capability to efficiently find suspected infringing models among tens of millions of models. In this paper, inspired by the hash-based image retrieval methods, we propose a perceptual hashing algorithm for convolutional neural networks (CNNs). The proposed perceptual hashing algorithm can convert the weights of CNNs to fixed-length binary hash codes so that the lightly modified version has the similar hash code as the original model. By comparing the similarity of a pair of hash codes between a query model and a test model in the model library, the similar versions of a query model can be retrieved efficiently. To the best of our knowledge, this is the first perceptual hashing algorithm for CNNs. The experiment performed on a model library containing 3,565 models indicates that our proposed perceptual hashing scheme has a superior copy detection performance.

Convolutional Neural Network Copy Detection with Neural Network Perceptual Hashing

In recent years, many model intellectual property (IP) proof methods for IP protection have been proposed, such as model watermarking and model fingerprinting. However, as an important part of the model IP protection system, the model copy detection task has not received enough attention. With the increasing number of neural network models transmitted and deployed on the Internet, the search for similar models is in great demand, which concurrently triggers the security problem of copy detection of models for IP protection. Due to the high computational complexity, both model watermarking and model fingerprinting lack the capability to efficiently find suspected infringing models among tens of millions of models. In this paper, inspired by the hash-based image retrieval methods, we propose a perceptual hashing algorithm for convolutional neural networks (CNNs). The proposed perceptual hashing algorithm can convert the weights of CNNs to fixed-length binary hash codes so that the lightly modified version has the similar hash code as the original model. By comparing the similarity of a pair of hash codes between a query model and a test model in the model library, the similar versions of a query model can be retrieved efficiently. To the best of our knowledge, this is the first perceptual hashing algorithm for CNNs. The experiment performed on a model library containing 3,565 models indicates that our proposed perceptual hashing scheme has a superior copy detection performance.

Feature Re-Learning for Video Recommendation

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. The application is in video recommendation, video annotation, Category or near-duplicate video retrieval, video copy detection and so on. In order to estimate video relevance previous works utilize textual content of videos and lead to poor performance. The proposed method is feature re-learning for video relevance prediction. This work focus on the visual contents to predict the relevance between two videos. A given feature is projected into a new space by an affine transformation. Different from previous works this use a standard triplet ranking loss that optimize the projection process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, propose a data augmentation strategy which works directly on video features. The multi-level augmentation strategy works for video features, which benefits the feature relearning. The proposed augmentation strategy can be flexibly used for frame-level or video-level features. The loss function that consider the absolute similarity of positive pairs and supervise the feature re-learning process and a new formula for video relevance computation.

Hybrid Method for Detecting Duplicate Image by Using Image Retrieval Technique in Data Mining

Duplicated images cause several problems in online sites, so these demand special attention. To address the disadvantages of frames copy detection, the Hybrid Method of Detecting Duplicate Image by Using Image Retrieval Technique in Data Mining was proposed. We use the new method of eliminating duplicates in this example. To address the disadvantages of frames copy detection, the Hybrid Method of Detecting Duplicate Image by Using Image Retrieval Technique in Data Mining was proposed. The new method of eliminating duplicates in this example has proposed. Using this method, you can get rid of frames that aren't relevant to the video. This makes for more precise and faster video retrieval with fewer duplicates. As a back end, this technique is implemented in C# and SQL. The findings are put to the test and compared to the current SIFT process. The results showed that the output improved accuracy while reducing storage space, computational time, and memory use.