Related papers: Coevolving Representations in Joint Image-Feature …
We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep…
Pre-trained diffusion models have demonstrated remarkable proficiency in synthesizing images across a wide range of scenarios with customizable prompts, indicating their effective capacity to capture universal features. Motivated by this,…
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…
Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions…
Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…
Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on…
Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As noise levels increase, the outputs of the trained model exhibit…
Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual…
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…
Diffusion models have recently been investigated as powerful generative solvers for image dehazing, owing to their remarkable capability to model the data distribution. However, the massive computational burden imposed by the retraining of…
Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both…
Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…
Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…
Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications…
Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on…
Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners. This paper decomposes the interrelation between the generative…
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive…
Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven…
Low-light image enhancement aims to improve the visibility of degraded images to better align with human visual perception. While diffusion-based methods have shown promising performance due to their strong generative capabilities. However,…
While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and…