Related papers: Deep Spherical Quantization for Image Search
Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…
Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…
Over the years, the use of superpixel segmentation has become very popular in various applications, serving as a preprocessing step to reduce data size by adapting to the content of the image, regardless of its semantic content. While the…
Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision. Quantization reduces model size and inference…
Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature…
The training of deep neural networks (DNNs) requires intensive resources both for computation and for storage performance. Thus, DNNs cannot be efficiently applied to mobile phones and embedded devices, which seriously limits their…
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed…
Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise…
Fine-grained image hashing is a challenging problem due to the difficulties of discriminative region localization and hash code generation. Most existing deep hashing approaches solve the two tasks independently. While these two tasks are…
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval. The framework is a two-step hashing approach…
Quantization is an effective method for reducing memory footprint and inference time of Neural Networks, e.g., for efficient inference in the cloud, especially at the edge. However, ultra low precision quantization could lead to significant…
Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which…
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world…
Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory…
In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes visually and semantically coherent image segments. We use binary encoding of…
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning…
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…
Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gear the needs that the deep learning algorithms could be run…
Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…