Related papers: End-to-End Supervised Product Quantization for Ima…

Despite the widespread use of text-to-image diffusion models across various tasks, their computational and memory demands limit practical applications. To mitigate this issue, quantization of diffusion models has been explored. It reduces…

Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable real-world…

This paper proposes a novel matrix quantization method, Binary Quadratic Quantization (BQQ). In contrast to conventional first-order quantization approaches, such as uniform quantization and binary coding quantization, that approximate…

Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success in table detection. However, a significant amount of labeled…

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used…

Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful…

In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of…

Recently, Babenko and Lempitsky introduced Additive Quantization (AQ), a generalization of Product Quantization (PQ) where a non-independent set of codebooks is used to compress vectors into small binary codes. Unfortunately, under this…

Diffusion models (DMs) have emerged as promising approaches for sequential recommendation due to their strong ability to model data distributions and generate high-quality items. Existing work typically adds noise to the next item and…

We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach…

The Probabilistic Object Detection Challenge evaluates object detection methods using a new evaluation measure, Probability-based Detection Quality (PDQ), on a new synthetic image dataset. We present our submission to the challenge, a…

Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial…

High-dimensional Nearest Neighbor (NN) search is central in multimedia search systems. Product Quantization (PQ) is a widespread NN search technique which has a high performance and good scalability. PQ compresses high-dimensional vectors…

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…

Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when the domain is…

Deep learning techniques have achieved specific results in recording device source identification. The recording device source features include spatial information and certain temporal information. However, most recording device source…

Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a…

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow…

This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current…

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…