United States

We propose a novel solution for unpaired image-to-image (I2I) translation. To translate complex images with a wide range of objects to a different domain, recent approaches often use the object annotations to perform per-class source-to-target style mapping. However, there remains a point for us to exploit in the I2I. An object in each class consists of multiple components, and all the sub-object components have different characteristics. For example, a car in CAR class consists of a car body, tires, windows and head and tail lamps, etc., and they should be handled separately for realistic I2I translation. The simplest solution to the problem will be to use more detailed annotations with sub-object component annotations than the simple object annotations, but it is not possible. The key idea of this paper is to bypass the sub-object component annotations by leveraging the original style of the input image because the original style will include the information about the characteristics of the sub-object components. Specifically, for each pixel, we use not only the per-class style gap between the source and target domains but also the pixel’s original style to determine the target style of a pixel. To this end, we present Style Harmonization for unpaired I2I translation (SHUNIT). Our SHUNIT generates a new style by harmonizing the target domain style retrieved from a class memory and an original source image style. Instead of direct source-to-target style mapping, we aim for source and target styles harmonization. We validate our method with extensive experiments and achieve state-of-the-art performance on the latest benchmark sets. The source code and model will be available online. We included the code of our model in the supplementary material.

AAAI 2023

SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation

image & video synthesis

applications

computational photography

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Social networks are essentially in a graph structure where persons act as nodes and the edges connecting nodes denote social relations. The prediction of social relations, therefore, relies on the context in graphs to model the higher-order constraints among relations, which has not been exploited sufficiently by previous works, however. In this paper, we formulate the paradigm of the higher-order constraints in social relations into triangular relational closed-loop structures, i.e., triangular constraints, and further introduce the triangular reasoning graph attention network (TRGAT). Our TRGAT employs the attention mechanism to aggregate features with triangular constraints in the graph, thereby exploiting the higher-order context to reason social relations iteratively. Besides, to acquire better feature representations of persons, we introduce node contrastive learning into relation reasoning. Experimental results show that our method outperforms existing approaches significantly, with higher accuracy and better consistency in generating social relation graphs.

Social Relation Reasoning Based on Triangular Constraints

Sports analytics has captured increasing attention since analysis of the various data enables insights for training strategies, player evaluation, etc. In this paper, we focus on predicting what types of returning strokes will be made, and where players will move to based on previous strokes. As this problem has not been addressed to date, movement forecasting can be tackled through sequence-based and graph-based models by formulating as a sequence prediction task. However, existing sequence-based models neglect the effects of interactions between players, and graph-based models still suffer from multifaceted perspectives on the next movement. Moreover, there is no existing work on representing strategic relations among players' shot types and movements. To address these challenges, we first introduce the procedure of the Player Movements (PM) graph to exploit the structural movements of players with strategic relations. Based on the PM graph, we propose a novel Dynamic Graphs and Hierarchical Fusion for Movement Forecasting model (DyMF) with interaction style extractors to capture the mutual interactions of players themselves and between both players within a rally, and dynamic players' tactics across time. In addition, hierarchical fusion modules are designed to incorporate the style influence of both players and rally interactions. Extensive experiments show that our model empirically outperforms both sequence- and graph-based methods and demonstrate the practical usage of movement forecasting. Code is available at https://github.com/wywyWang/CoachAI-Projects/tree/main/Movement%20Forecasting.

Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton

A temporal knowledge graph (TKG) stores the events derived from the data involving time. Predicting events is extremely challenging due to the time-sensitive property of events. Besides, the previous TKG completion (TKGC) approaches cannot represent both the timeliness and the causality properties of events, simultaneously. To address these challenges, we propose a Logic and Commonsense-Guided Embedding model (LCGE) to jointly learn the time-sensitive representation involving timeliness and causality of events, together with the time-independent representation of events from the perspective of commonsense. Specifically, we design a temporal rule learning algorithm to construct a rule-guided predicate embedding regularization strategy for learning the causality among events. Furthermore, we could accurately evaluate the plausibility of events via auxiliary commonsense knowledge. The experimental results of TKGC task illustrate the significant performance improvements of our model compared with the existing approaches. More interestingly, our model is able to provide the explainability of the predicted results in the view of causal inference. The appendix, source code and datasets of this paper are available at https://github.com/ngl567/LCGE.

Logic and Commonsense-Guided Temporal Knowledge Graph Completion

Self-Supervised Video Hashing (SSVH) models learn to generate short binary representations for videos without ground-truth supervision, facilitating large-scale video retrieval efficiency and attracting increasing research attention. The success of SSVH lies in the understanding of video content and the ability to capture the semantic relation among unlabeled videos. Typically, state-of-the-art SSVH methods consider these two points in a two-stage training pipeline, where they firstly train an auxiliary network by instance-wise mask-and-predict tasks and secondly train a hashing model to preserve the pseudo-neighborhood structure transferred from the auxiliary network. This consecutive training strategy is inflexible and also unnecessary. In this paper, we propose a simple yet effective one-stage SSVH method called ConMH, which incorporates video semantic information and video similarity relationship understanding in a single stage. To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames. Particularly, we find that a higher masking ratio helps video understanding. Besides, we fully exploit the similarity relationship between videos by maximizing agreement between two augmented views of a video, which contributes to more discriminative and robust hash codes. Extensive experiments on three large-scale video datasets (\ie, FCVID, ActivityNet and YFCC) indicate that ConMH achieves state-of-the-art results. 

Contrastive Masked Autoencoders for Self-Supervised Video Hashing

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised pretraining framework where users may flexibly combine the modalities of vision, speech, and language into unified and general-purpose vector representations. In this framework, data from each modality are first given to pretrained single-modality encoders. The encoder outputs are then integrated with a multimodal fusion network, which uses novel merge- and co-attention mechanisms to effectively combine information from the different modalities. The entire system is pretrained end-to-end with new objectives including masked modality unit modeling and cross-modality contrastive learning. Unlike previous research using only video for pretraining, the i-Code framework can dynamically process single, dual, and triple-modality data during training and inference, flexibly projecting different combinations of modalities into a single representation space. Experimental results demonstrate how i-Code can outperform state-of-the-art techniques on five multimodal understanding tasks and single-modality benchmarks, improving by as much as 11\% and demonstrating the power of integrative multimodal pretraining.

i-Code: An Integrative and Composable Multimodal Learning Framework

Unsupervised meta-learning aims to learn the meta knowledge from unlabeled data and rapidly adapt to novel tasks. However, existing approaches may be misled by the  context-bias (e.g. background) from the training data. In this paper, we abstract the unsupervised meta-learning problem into a Structural Causal Model (SCM) and point out that such bias arises due to hidden confounders. To eliminate the confounders, we define the priors are \textit{conditionally} independent, learn the relationships between priors and intervene on them with casual factorization. Furthermore, we propose Causal Meta VAE (CMVAE) that encodes the priors into latent codes in the causal space and learns their relationships simultaneously to achieve the downstream few-shot image classification task. Results on toy datasets and three benchmark datasets demonstrate that our method can remove the context-bias and it outperforms other state-of-the-art unsupervised meta-learning algorithms because of bias-removal. Code is available at \url{https://github.com/GuodongQi/CMVAE}.

CMVAE: Causal Meta VAE for Unsupervised Meta-Learning

Automatic assembly is a promising research topic in 3D computer vision and robotics. Existing works focus on generating assembly (e.g., IKEA furniture) from scratch with a set of parts, namely 3D part assembly. In practice, there are higher demands for the robot to take over and finish an incomplete assembly (e.g., a half-assembled IKEA furniture) with an off-the-shelf toolkit, especially in human-robot and multi-agent collaborations. Compared to 3D part assembly, it is more complicated in nature and remains unexplored yet. The robot must understand the incomplete structure, infer what parts are missing, single out the correct parts from the toolkit and finally, assemble them with appropriate poses to finish the incomplete assembly. Geometrically similar parts in the toolkit can interfere, and this problem will be exacerbated with more missing parts. To tackle this issue, we propose a novel task called 3D assembly completion. Given an incomplete assembly, it aims to find its missing parts from a toolkit and predict the 6-DoF poses to make the assembly complete. To this end, we propose FiT, a framework for Finishing the incomplete 3D assembly with Transformer. We employ the encoder to model the incomplete assembly into memories. Candidate parts interact with memories in a memory-query paradigm for final candidate classification and pose prediction. Bipartite part matching and symmetric transformation consistency are embedded to refine the completion. For reasonable evaluation and further reference, we design two standard toolkits of different difficulty, containing different compositions of candidate parts. We conduct extensive comparisons with several baseline methods and ablation studies, demonstrating the effectiveness of the proposed method.

3D Assembly Completion

Simulating physical network paths (e.g., Internet) is a cornerstone research problem in the emerging sub-field of AI-for-networking. We seek a model that generates end-to-end packet delay values in response to the time-varying load offered by a sender, which is typically a function of the previously output delays. We formulate a novel ML problem at the intersection of dynamical systems, sequential decision making, and time-series generative modeling. The problem setting is unique, and renders the state-of-the-art neural generative modeling work in the text and time-series domains inapplicable, or ineffective. We propose a novel grey-box approach to network simulation that embeds the semantics of physical network path in a new RNN-style architecture called Recurrent Buffering Unit, providing the interpretability of standard network simulator tools, the power of neural models, the efficiency of SGD-based techniques for learning, and yielding promising results on synthetic and real-world network traces.

Simulating Network Paths with Recurrent Buffering Units

Incorporating sequence-to-sequence models into history-based Reinforcement Learning (RL) provides a general way to extend RL to partially-observable tasks. This method compresses history spaces according to the correlations between historical observations and the rewards. However, they do not adjust for the confounding correlations caused by data sampling and assign high beliefs to uninformative historical observations, leading to limited compression of history spaces. Counterfactual Inference (CI), which estimates causal effects by single-variable intervention, is a promising way to adjust for confounding. However, it is computationally infeasible to directly apply the single-variable intervention to a huge number of historical observations. This paper proposes to perform CI on observation sub-spaces instead of single observations and develop a coarse-to-fine CI algorithm, called Tree-based History Counterfactual Inference (T-HCI), to reduce the number of interventions exponentially. We show that T-HCI is computationally feasible in practice and brings significant sample efficiency gains in various challenging partially-observable tasks, including Maze, BabyAI, and robot manipulation tasks.

Fast Counterfactual Inference for History-Based Reinforcement Learning

Voxel grid representation of 3D scene properties has been widely used to improve the training or rendering speed of the Neural Radiance Fields (NeRF) while at the same time achieving high synthesis quality. However, these methods accelerate the original NeRF at the expense of extra storage demand, which hinders their applications in many scenarios. To solve this limitation, we present TinyNeRF, a three-stage pipeline: frequency domain transformation, pruning and quantization that work together to reduce the storage demand of the voxel grids with little to no effects on their speed and synthesis quality. Based on the prior knowledge of visual signals sparsity in the frequency domain, we convert the original voxel grids in the frequency domain via block-wise discrete cosine transformation (DCT). Next, we apply pruning and quantization to enforce the DCT coefficients to be sparse and low-bit. Our method can be optimized from scratch in an end-to-end manner, and can typically compress the original models by 2 orders of magnitude with minimal sacrifice on speed and synthesis quality.

Premium content

SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation

Downloads

Next from AAAI 2023

Social Relation Reasoning Based on Triangular Constraints

Similar lecture

EMEF: Ensemble Multi-Exposure Image Fusion