Related papers: Beyond the Last Layer: Multi-Layer Representation …
In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…
Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…
Deep learning based fusion methods have been achieving promising performance in image fusion tasks. This is attributed to the network architecture that plays a very important role in the fusion process. However, in general, it is hard to…
As the rapid growth of high-speed and deep-tissue imaging in biomedical research, it is urgent to find a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional…
3D instance segmentation aims to predict a set of object instances in a scene and represent them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…
We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate…
Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that…
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders:…
We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…
Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs)…
Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…
LiDAR-based perception is central to autonomous driving and robotics, yet raw point clouds remain highly vulnerable to noise, occlusion, and adversarial corruptions. Autoencoders offer a natural framework for denoising and reconstruction,…
Integrating the different data modalities of cancer patients can significantly improve the predictive performance of patient survival. However, most existing methods ignore the simultaneous utilization of rich semantic features at different…
The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explored incorporating Vision Foundation Models (VFMs) into the tokenizers training via…
Transformer-based pre-trained language models have proven to be effective for learning contextualized language representation. However, current approaches only take advantage of the output of the encoder's final layer when fine-tuning the…
This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA…
Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images. This paper proposes a novel auto-encoder (AE) based fusion network. The core idea is…
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a…
This study presents Latent Diffusion Autoencoder (LDAE), a novel encoder-decoder diffusion-based framework for efficient and meaningful unsupervised learning in medical imaging, focusing on Alzheimer disease (AD) using brain MR from the…