Related papers: Joint Hierarchical Priors and Adaptive Spatial Res…

Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating this inductive bias into ViTs, not through an architectural…

This paper presents a cross channel context model for latents in deep image compression. Generally, deep image compression is based on an autoencoder framework, which transforms the original image to latents at the encoder and recovers the…

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed…

Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. However, there are still gaps in both performance and computational cost between…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high level vision applications such as recognition and understanding. However, it is rarely used to…

Iris restoration from complexly degraded iris images, aiming to improve iris recognition performance, is a challenging problem. Due to the complex degradation, directly training a convolutional neural network (CNN) without prior cannot…

As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking…

In the evolving landscape of 6G networks, semantic communications are poised to revolutionize data transmission by prioritizing the transmission of semantic meaning over raw data accuracy. This paper presents a Vision Transformer…

Compressed Sensing MRI reconstructs images of the body's internal anatomy from undersampled measurements, thereby reducing scan time. Recently, deep learning has shown great potential for reconstructing high-fidelity images from highly…

Transformers have demonstrated promising performance in computer vision tasks, including image super-resolution (SR). The quadratic computational complexity of window self-attention mechanisms in many transformer-based SR methods forces the…

Convolutional neural networks (CNNs) play a key role in deep learning applications. However, the large storage overheads and the substantial computation cost of CNNs are problematic in hardware accelerators. Computing-in-memory (CIM)…

Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural…

We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn inference networks to predict a compressible latent representation…

Error correction codes (ECC) are crucial for ensuring reliable information transmission in communication systems. Choukroun & Wolf (2022b) recently introduced the Error Correction Code Transformer (ECCT), which has demonstrated promising…

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…

Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transformers, which are inherently rigid. Standard CNN kernels and…

Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Since the…

We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural…