相关论文: The Neurally-Guided Shape Parser: Grammar-based La…

The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly…

Multi-label image recognition is a fundamental task in computer vision. Recently, Vision-Language Models (VLMs) have made notable advancements in this area. However, previous methods fail to effectively leverage the rich knowledge in…

Calibrating the confidence of neural network classifiers is essential for quantifying the reliability of their predictions during inference. However, conventional Gaussian Process (GP) calibration methods often fail to capture the internal…

3D ultrasound (US) can facilitate detailed prenatal examinations for fetal growth monitoring. To analyze a 3D US volume, it is fundamental to identify anatomical landmarks of the evaluated organs accurately. Typical deep learning methods…

Accurate face parsing under extreme viewing angles remains a significant challenge due to limited labeled data in such poses. Manual annotation is costly and often impractical at scale. We propose a novel label refinement pipeline that…

Radiologists rely on anatomical understanding to accurately delineate pathologies, yet most current deep learning approaches use pure pattern recognition and ignore the anatomical context in which pathologies develop. To narrow this gap, we…

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for…

We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula. Learning in this setting proceeds by first computing (a subset of) the possible…

Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use…

The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics. For a system to accomplish this, it must autonomously identify grasping locations by using information from…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

Assembly-based tools provide a powerful modeling paradigm for non-expert shape designers. However, choosing a component from a large shape repository and aligning it to a partial assembly can become a daunting task. In this paper we…

We propose a universal Graph Neural Network architecture which can be trained as an end-2-end search heuristic for any Constraint Satisfaction Problem (CSP). Our architecture can be trained unsupervised with policy gradient descent to…

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method,…

Deep convolution neural networks (CNN) have demonstrated advanced performance on single-label image classification, and various progress also have been made to apply CNN methods on multi-label image classification, which requires to…

There have been recent efforts for incorporating Graph Neural Network models for learning full-stack solvers for constraint satisfaction problems (CSP) and particularly Boolean satisfiability (SAT). Despite the unique representational power…

Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node…

Lesion segmentation on nasal endoscopic images is challenging due to its complex lesion features. Fully-supervised deep learning methods achieve promising performance with pixel-level annotations but impose a significant annotation burden…

In a semi-supervised learning scenario, (possibly noisy) partially observed labels are used as input to train a classifier, in order to assign labels to unclassified samples. In this paper, we study this classifier learning problem from a…

With the rapid expansion of applied 3D computational vision, shape descriptors have become increasingly important for a wide variety of applications and objects from molecules to planets. Appropriate shape descriptors are critical for…