Related papers: Semantic Alignment and Reinforcement for Data-Free…

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent…

Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining. Nevertheless, current PTQ methods for Vision Transformers…

Semantic image synthesis enables control over unconditional image generation by allowing guidance on what is being generated. We conditionally synthesize the latent space from a vector quantized model (VQ-model) pre-trained to autoencode…

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional…

Neural network quantization is an effective way to compress deep models and improve their execution latency and energy efficiency, so that they can be deployed on mobile or embedded devices. Existing quantization methods require original…

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a…

Vector Quantization (VQ) is a well-known technique in deep learning for extracting informative discrete latent representations. VQ-embedded models have shown impressive results in a range of applications including image and speech…

Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…

Post-training quantization (PTQ) for vision transformers (ViTs) has received increasing attention from both academic and industrial communities due to its minimal data needs and high time efficiency. However, many current methods fail to…

While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value…

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping…

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising…

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how…

Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real applications raises critical challenges including the high…

The DETR-like segmentors have underpinned the most recent breakthroughs in semantic segmentation, which end-to-end train a set of queries representing the class prototypes or target segments. Recently, masked attention is proposed to…

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment methods like PSNR, SSIM, and LPIPS. However, these…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Recent advances in fMRI-based image reconstruction have achieved remarkable photo-realistic fidelity. Yet, a persistent limitation remains: while reconstructed images often appear naturalistic and holistically similar to the target stimuli,…