Related papers: Generating Attribution Maps with Disentangled Mask…

In this paper, we present a novel differential morph detection framework, utilizing landmark and appearance disentanglement. In our framework, the face image is represented in the embedding domain using two disentangled but complementary…

We introduce DiMPLe (Disentangled Multi-Modal Prompt Learning), a novel approach to disentangle invariant and spurious features across vision and language modalities in multi-modal learning. Spurious correlations in visual data often hinder…

Experts use retinal images and vessel trees to detect and diagnose various eye, blood circulation, and brain-related diseases. However, manual segmentation of retinal images is a time-consuming process that requires high expertise and is…

Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this…

This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…

Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating amount of images,…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

We introduce DiffBMP, a scalable and efficient differentiable rendering engine for a collection of bitmap images. Our work addresses a limitation that traditional differentiable renderers are constrained to vector graphics, given that most…

Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs.…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive…

Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient…

We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification. Our…

Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce high-quality…

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of…

In this paper, it is shown that an auto-encoder using optimal reconstruction significantly outperforms a conventional auto-encoder. Optimal reconstruction uses the conditional mean of the input given the features, under a maximum entropy…

The classification decisions of neural networks can be misled by small imperceptible perturbations. This work aims to explain the misled classifications using saliency methods. The idea behind saliency methods is to explain the…

We propose a novel approach to denoising diffusion magnetic resonance images (dMRI) using convolutional neural networks, that exploits the benefits of data acquired at multiple b-values to offset the need for many redundant observations.…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple…

The ability to differentiate through optimization problems has unlocked numerous applications, from optimization-based layers in machine learning models to complex design problems formulated as bilevel programs. It has been shown that…