21 accepted papers
In multi-output structured prediction tasks, while only one ground truth label may be provided in the training data, multiple equally valid outputs may be possible, making reliable evaluation a persistent challenge. We postulate that human evaluators implicitly use task-specific invariants, e.g., ob
Roadside perception datasets are typically constructed via cooperative labeling between synchronized vehicle and roadside frame pairs, but real deployment is often limited roadside-only data due to hardware and privacy constraints. The observation that even human experts struggle to produce accurate
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and p
The Cosmic Microwave Background (CMB) radiation is a pillar of modern cosmology that gives rise to a better understanding of the fundamental parameters of the universe. While the astrophysics community has developed computational methods to extract this signal from data, these methods have limited s…
Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity…
Tractable probabilistic models (TPMs) have attracted substantial research interest in recent years, particularly because of their ability to answer various reasoning queries in polynomial time. In this study, we focus on the distributionally robust learning of continuous TPMs and address the challen…
Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segmentation tasks. However, the traditional mean shift…
Temporal models such as Dynamic Bayesian Networks (DBNs) and Hidden Markov Models (HMMs) have been widely used to model time-dependent sequential data. Typically, these approaches limit focus to discrete domains, employ first-order Markov and stationary assumptions, and limit representational power…
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the segmentation mask of the grasped or pushed object after one action. I…
Historically, conditional random fields (CRFs) were popular tools in a variety of application areas from computer vision to natural language processing, but due to their higher computational cost and weaker practical performance, they have, in many situations, fallen out of favor and been replaced b…
Tractable models such as cutset networks and sum-product networks (SPNs) have become increasingly popular because they have superior predictive performance. Among them, cutset networks, which model the mechanics of Pearl’s cutset conditioning algorithm, demonstrate great scalability and prediction a…
Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been restricted to discrete domains owing to the complexity of inference in continuous domains. In this work, we…
Tractable probabilistic models (TPMs) are appealing because they admit polynomial-time inference for a wide variety of queries. In this work, we extend the cutset network (CN) framework, a powerful sub-class of TPMs that often outperforms probabilistic graphical models in terms of prediction accurac…
Maximum likelihood learning is a well-studied approach for fitting discrete Markov random fields (MRFs) to data. However, general purpose maximum likelihood estimation for fitting MRFs with continuous variables have only been studied in much more limited settings. In this work, we propose a generi…
Lifted inference algorithms exploit model symmetry to reduce computational cost in probabilistic inference. However, most existing lifted inference algorithms operate only over discrete domains or continuous domains with restricted potential functions. We investigate two approximate lifted variation…
Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the correlations between data points, which might be crucial for learni…
Statistical inference in Markov random fields (MRFs) is NP-hard in all but the simplest of cases. As a result, many algorithms, particularly in the case of discrete random variables, have been developed to perform approximate inference in practice. However, most of these methods scale poorly, cann…
Computing the partition function of an arbitrary graphical model is generally intractable. As a result, approximate inference techniques such as loopy belief propagation and expectation propagation are used to compute an approximation to the true partition function. However, due to general issues o…
We consider the problem of computing a restricted nonnegative matrix factorization (NMF) of an m\times n matrix X. Specifically, we seek a factorization X\approx BC, where the k columns of B are a subset of those from X and C\in\Re_{\geq 0}^{k\times n}. Equivalently, given the matrix X, consider t…
Many machine learning tasks require fitting probabilistic models over structured objects, such as pixel grids, matchings, and graph edges. Maximum likelihood estimation (MLE) for such domains is challenging due to the intractability of computing partition functions. One can resort to approximate mar…
Computing the MAP assignment in graphical models is generally intractable. As a result, for discrete graphical models, the MAP problem is often approximated using linear programming relaxations. Much research has focused on characterizing when these LP relaxations are tight, and while they are rel…