To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views, lighting, occlusio
ns, etc. In this paper, we tackle this challenge by introducing a spatio-temporal representation learning (STRL) framework, capable of learning from unlabeled 3D point clouds in a self-supervised fashion. Inspired by how infants learn from visual data in the wild, we explore the rich spatio-temporal cues derived from the 3D data. Specifically, STRL takes two temporally-correlated frames from a 3D point cloud sequence as the input, transforms it with the spatial data augmentation, and learns the invariant representation self-supervisedly. To corroborate the efficacy of STRL, we conduct extensive experiments on three types (synthetic, indoor, and outdoor) of datasets. Experimental results demonstrate that, compared with supervised learning methods, the learned self-supervised representation facilitates various models to attain comparable or even better performances while capable of generalizing pre-trained models to downstream tasks, including 3D shape classification, 3D object detection, and 3D semantic segmentation. Moreover, the spatio-temporal contextual cues embedded in 3D point clouds significantly improve the learned representations.
textit{Graph Neural Network} (GNN) is a promising approach for analyzing graph-structured data that tactfully captures their dependency information via node-level message passing. It has achieved state-of-the-art performances in many tasks, such as n
ode classification, graph matching, clustering, and graph generation. As GNNs operate on non-Euclidean data, their irregular data access patterns cause considerable computational costs and overhead on conventional architectures, such as GPU and CPU. Our analysis shows that GNN adopts a hybrid computing model. The textit{Aggregation} (or textit{Message Passing}) phase performs vector additions where vectors are fetched with irregular strides. The textit{Transformation} (or textit{Node Embedding}) phase can be either dense or sparse-dense matrix multiplication. In this work, We propose textit{VersaGNN}, an ultra-efficient, systolic-array-based versatile hardware accelerator that unifies dense and sparse matrix multiplication. By applying this single optimized systolic array to both aggregation and transformation phases, we have significantly reduced chip sizes and energy consumption. We then divide the computing engine into blocked systolic arrays to support the textit{Strassen}s algorithm for dense matrix multiplication, dramatically scaling down the number of multiplications and enabling high-throughput computation of GNNs. To balance the workload of sparse-dense matrix multiplication, we also introduced a greedy algorithm to combine sparse sub-matrices of compressed format into condensed ones to reduce computational cycles. Compared with current state-of-the-art GNN software frameworks, textit{VersaGNN} achieves on average 3712$times$ speedup with 1301.25$times$ energy reduction on CPU, and 35.4$times$ speedup with 17.66$times$ energy reduction on GPU.
Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its demanding but unique nature: a theoretic requirement on representing and reasoning based on spatial-temporal knowledge in mind, and an applied requirement on
a high-level cognitive system capable of navigating and acting in space and time. Recent works have focused on an abstract reasoning task of this kind -- Ravens Progressive Matrices (RPM). Despite the encouraging progress on RPM that achieves human-level performance in terms of accuracy, modern approaches have neither a treatment of human-like reasoning on generalization, nor a potential to generate answers. To fill in this gap, we propose a neuro-symbolic Probabilistic Abduction and Execution (PrAE) learner; central to the PrAE learner is the process of probabilistic abduction and execution on a probabilistic scene representation, akin to the mental manipulation of objects. Specifically, we disentangle perception and reasoning from a monolithic model. The neural visual perception frontend predicts objects attributes, later aggregated by a scene inference engine to produce a probabilistic scene representation. In the symbolic logical reasoning backend, the PrAE learner uses the representation to abduce the hidden rules. An answer is predicted by executing the rules on the probabilistic representation. The entire system is trained end-to-end in an analysis-by-synthesis manner without any visual attribute annotations. Extensive experiments demonstrate that the PrAE learner improves cross-configuration generalization and is capable of rendering an answer, in contrast to prior works that merely make a categorical choice from candidates.
We generalize the existing principle of the maximum Shannon entropy in reinforcement learning (RL) to weighted entropy by characterizing the state-action pairs with some qualitative weights, which can be connected with prior knowledge, experience rep
lay, and evolution process of the policy. We propose an algorithm motivated for self-balancing exploration with the introduced weight function, which leads to state-of-the-art performance on Mujoco tasks despite its simplicity in implementation.
In searching for a generalizable representation of temporally extended tasks, we spot two necessary constituents: the utility needs to be non-Markovian to transfer temporal relations invariant to a probability shift, the utility also needs to be lift
ed to abstract out specific grounding objects. In this work, we study learning such utility from human demonstrations. While inverse reinforcement learning (IRL) has been accepted as a general framework of utility learning, its fundamental formulation is one concrete Markov Decision Process. Thus the learned reward function does not specify the task independently of the environment. Going beyond that, we define a domain of generalization that spans a set of planning problems following a schema. We hence propose a new quest, Generalized Inverse Planning, for utility learning in this domain. We further outline a computational framework, Maximum Entropy Inverse Planning (MEIP), that learns non-Markovian utility and associated concepts in a generative manner. The learned utility and concepts form a task representation that generalizes regardless of probability shift or structural change. Seeing that the proposed generalization problem has not been widely studied yet, we carefully define an evaluation protocol, with which we illustrate the effectiveness of MEIP on two proof-of-concept domains and one challenging task: learning to fold from demonstrations.
This paper proposes to learn hierarchical compositional AND-OR model for interpretable image synthesis by sparsifying the generator network. The proposed method adopts the scene-objects-parts-subparts-primitives hierarchy in image representation. A s
cene has different types (i.e., OR) each of which consists of a number of objects (i.e., AND). This can be recursively formulated across the scene-objects-parts-subparts hierarchy and is terminated at the primitive level (e.g., wavelets-like basis). To realize this AND-OR hierarchy in image synthesis, we learn a generator network that consists of the following two components: (i) Each layer of the hierarchy is represented by an over-complete set of convolutional basis functions. Off-the-shelf convolutional neural architectures are exploited to implement the hierarchy. (ii) Sparsity-inducing constraints are introduced in end-to-end training, which induces a sparsely activated and sparsely connected AND-OR model from the initially densely connected generator network. A straightforward sparsity-inducing constraint is utilized, that is to only allow the top-$k$ basis functions to be activated at each layer (where $k$ is a hyper-parameter). The learned basis functions are also capable of image reconstruction to explain the input images. In experiments, the proposed method is tested on four benchmark datasets. The results show that meaningful and interpretable hierarchical representations are learned with better qualities of image synthesis and reconstruction obtained than baselines.
This work is about recognizing human activities occurring in videos at distinct semantic levels, including individual actions, interactions, and group activities. The recognition is realized using a two-level hierarchy of Long Short-Term Memory (LSTM
) networks, forming a feed-forward deep architecture, which can be trained end-to-end. In comparison with existing architectures of LSTMs, we make two key contributions giving the name to our approach as Confidence-Energy Recurrent Network -- CERN. First, instead of using the common softmax layer for prediction, we specify a novel energy layer (EL) for estimating the energy of our predictions. Second, rather than finding the common minimum-energy class assignment, which may be numerically unstable under uncertainty, we specify that the EL additionally computes the p-values of the solutions, and in this way estimates the most confident energy minimum. The evaluation on the Collective Activity and Volleyball datasets demonstrates: (i) advantages of our two contributions relative to the common softmax and energy-minimization formulations and (ii) a superior performance relative to the state-of-the-art approaches.
In this paper, we present an approach for robot learning of social affordance from human activity videos. We consider the problem in the context of human-robot interaction: Our approach learns structural representations of human-human (and human-obje
ct-human) interactions, describing how body-parts of each agent move with respect to each other and what spatial relations they should maintain to complete each sub-event (i.e., sub-goal). This enables the robot to infer its own movement in reaction to the human body motion, allowing it to naturally replicate such interactions. We introduce the representation of social affordance and propose a generative model for its weakly supervised learning from human demonstration videos. Our approach discovers critical steps (i.e., latent sub-events) in an interaction and the typical motion associated with them, learning what body-parts should be involved and how. The experimental results demonstrate that our Markov Chain Monte Carlo (MCMC) based learning algorithm automatically discovers semantically meaningful interactive affordance from RGB-D videos, which allows us to generate appropriate full body motion for an agent.
