Related papers: Efficient reversible data hiding via two layers of…

Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to…

In this paper we propose a new data hiding technique. The new technique uses steganography and cryptography on images with a size of 256x256 pixels and an 8-bit grayscale format. There are design restrictions such as a fixed-size cover…

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to…

We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures…

Data hiding is one widely used approach for protecting authentication and ownership. Most multimedia content like images and videos are transmitted or saved in the compressed form. This kind of lossy compression, such as JPEG, can destroy…

We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimation as an implicit layer, which allows us to avoid…

In view of the frequent multimedia data transfer authentication and protection of images has gained importance in todays world. In this paper we propose a new watermarking technique, based on bit plane, which enhances robustness and…

The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for…

The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural details. Despite the improvements observed in existing learning-based methods…

Hashing has been recognized as an efficient representation learning method to effectively handle big data due to its low computational complexity and memory cost. Most of the existing hashing methods focus on learning the low-dimensional…

As an emerging concept, steganography without embedding (SWE) hides a secret message without directly embedding it into a cover. Thus, SWE has the unique advantage of being immune to typical steganalysis methods and can better protect the…

Data hiding with deep neural networks (DNNs) has experienced impressive successes in recent years. A prevailing scheme is to train an autoencoder, consisting of an encoding network to embed (or transform) secret messages in (or into) a…

Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g.,…

Recently, deep learning-based image compression has made signifcant progresses, and has achieved better ratedistortion (R-D) performance than the latest traditional method, H.266/VVC, in both subjective metric and the more challenging…

As the multimedia and internet technologies are growing fast, the transmission of digital media plays an important role in communication. The various digital media like audio, video and images are being transferred through internet. There…

Data hiding is the art of concealing messages with limited perceptual changes. Recently, deep learning has enriched it from various perspectives with significant progress. In this work, we conduct a brief yet comprehensive review of…

t-SNE is a popular tool for embedding multi-dimensional datasets into two or three dimensions. However, it has a large computational cost, especially when the input data has many dimensions. Many use t-SNE to embed the output of a neural…

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…

Deep metric learning (DML) is a popular approach for images retrieval, solving verification (same or not) problems and addressing open set classification. Arguably, the most common DML approach is with triplet loss, despite significant…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…