United States

This paper proposes an unsupervised multi-exposure image fusion (MEF) method via contrastive learning, termed as MEF-CL. It breaks exposure limits and performance bottleneck faced by existing methods. MEF-CL firstly designs similarity constraints to preserve contents in source images. It eliminates the need for ground truth (actually not exist and created artificially) and thus avoids negative impacts of inappropriate ground truth on performance and generalization. Moreover, we explore a latent feature space and apply contrastive learning in this space to guide fused image to approximate normal-light samples and stay away from inappropriately exposed ones. In this way, characteristics of fused images (e.g., illumination, colors) can be further improved without being subject to source images. Therefore, MEF-CL is applicable to image pairs of any multiple exposures rather than a pair of under-exposed and over-exposed images mandated by existing methods. By alleviating dependence on source images, MEF-CL shows better generalization for various scenes. Consequently, our results exhibit appropriate illumination, detailed textures, and saturated colors. Qualitative, quantitative, and ablation experiments validate the superiority and generalization of MEF-CL. Our code is publicly available at https://github.com/hanna-xu/MEF-CL.

AAAI 2023

Unsupervised Multi-exposure Image Fusion Breaking Exposure Limits via Contrastive Learning

multi-exposure images

image fusion

contrastive learning

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

We study various models for the one-dimensional multi-stage facility location problems with transient agents, where a transient agent arrives in some stage and stays for a number of consecutive stages. In the problems, we need to serve each agent in one of their stages by determining the location of the facility at each stage. In the first model, we assume there is no cost for moving the facility across the stages. We focus on optimal algorithms to minimize both the social cost objective, defined as the total distance of all agents to the facility over all stages, and the maximum cost objective, defined as the max distance of any agent to the facility over all stages. For each objective, we give a slice-wise polynomial (XP) algorithm (i.e., solvable in m^f(k) for some fixed parameter k and computable function f, where m is the input size) and show that there is a polynomial-time algorithm when a natural first-come-first-serve (FCFS) order of agent serving is enforced. We then consider the mechanism design problem, where the agents' locations and arrival stages are private, and design a group strategy-proof mechanism that achieves good approximation ratios for both objectives and settings with and without FCFS ordering. In the second model, we consider the facility's moving cost between adjacent stages under the social cost objective, which accounts for the total moving distance of the facility. Correspondingly, we design XP (and polynomial time) algorithms and a group strategy-proof mechanism for settings with or without the FCFS ordering.  

Multi-Stage Facility Location Problems with Transient Agents

Amodal instance segmentation aims to infer the amodal mask, including both the visible part and occluded part of each object instance. Predicting the occluded parts is challenging. Existing methods often produce incomplete amodal boxes and amodal masks, probably due to lacking visual evidences to expand the boxes and masks. To this end, we propose a prior-guided expansion framework, which builds on a two-stage segmentation model (i.e., Mask R-CNN) and performs box-level (resp., pixel-level) expansion for amodal box (resp., mask) prediction, by retrieving regression (resp., flow) transformations from a memory bank of expansion prior. We conduct extensive experiments on KINS, D2SA, and COCOA cls datasets, which show the effectiveness of our method.

Amodal Instance Segmentation via Prior-guided Expansion

Trajectory similarity computation is a fundamental function in many applications of spatial data analysis. However, most existing methods are designed for trajectories in Euclidean space, ignoring the fact that trajectories in real applications are usually generated on the road networks. In this paper, we study the trajectory similarity computation on road networks with deep learning.
To jointly capture properties of trajectories and road networks, we propose a novel framework \textbf{GRLSTM} (\textbf{G}raph-based \textbf{R}esidual-\textbf{LSTM}), which employs knowledge graph embedding (KGE), graph neural network (GNN), and incorporates the residual network into the multi-layer LSTM (Residual-LSTM). In particular, we study multiple relations of Point-of-Interest (PoI) by constructing a PoI knowledge graph since PoIs may be in the trajectory or in the road network. To integrate multiple relations of each PoI, KGE is introduced to learn PoI embedddings and relation embeddings to build the PoI fusion graph. 
Then, GNN is applied to capture the topology structure information of the PoI fusion graph. Finally, the trajectory embeddings are learned in Residual-LSTM.
To further improve the accuracy and robustness of final trajectory embeddings, we design two new neighbor-based loss functions to optimize our model, i.e., PoI loss function and trajectory-PoI loss function. We conduct a comprehensive evaluation using different real-world trajectory datasets. The experimental results show that GRLSTM significantly outperforms all  state-of-the-art methods.

GRLSTM: Trajectory Similarity Computation with Graph-based Residual LSTM

Sarcasm is a sophisticated linguistic phenomenon that is prevalent on today's social media platforms. Multi-modal sarcasm detection aims to identify whether a given sample with multi-modal information (i.e., text and image) is sarcastic. This task's key lies in capturing both inter- and intra-modal incongruities within the same context. Although existing methods have achieved compelling success, they are disturbed by irrelevant information extracted from the whole image and text, or overlooking some important information due to the incomplete input. To address these limitations, we propose a Mutual-enhanced Incongruity Learning Network for multi-modal sarcasm detection, named MILNet. In particular, we design a local semantic-guided incongruity learning module and a global incongruity learning module. Moreover, we introduce a mutual enhancement module to take advantage of the underlying consistency between the two modules to boost the performance. Extensive experiments on a widely-used dataset demonstrate the superiority of our model over cutting-edge methods.

Mutual-enhanced Incongruity Learning Network for Multi-modal Sarcasm Detection

Question Answering (QA) is a task that entails reasoning over natural language contexts, and many relevant works augment language models (LMs) with graph neural networks (GNNs) to encode the Knowledge Graph (KG) information. However, most existing GNN-based modules for QA do not take advantage of rich relational information of KGs and depend on limited information interaction between the LM and the KG. To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner. Specifically, QAT constructs Meta-Path tokens, which learn relation-centric embeddings based on diverse structural and semantic relations. Then, our Relation-Aware Self-Attention module comprehensively integrates different modalities via the Cross-Modal Relative Position Bias, which guides information exchange between relevant entities of different modalities. We validate the effectiveness of QAT on commonsense question answering datasets like CommonsenseQA and OpenBookQA, and on a medical question answering dataset, MedQA-USMLE. On all the datasets, our method achieves state-of-the-art performance. Our code is available at http://github.com/mlvlab/QAT.

Relation-aware Language-Graph Transformer for Question Answering

A central computational problem in the realm of automata theory is the problem of determining whether a finite automaton A has a synchronizing word. This problem has found applications in a variety of subfields of artificial intelligence, such as robotics, game theory, and the theory of multi-agent systems. In this work, we study this problem within the framework of diversity of solutions, an up-and-coming trend in the field of artificial intelligence where the goal is to compute a set of solutions that are sufficiently distinct from one another. In our
work, the language L is specified by a finite automaton B given at the input. First, we define a notion of diversity of solutions that is suitable to the context of synchronization. Subsequently, we show that for each fixed r ∈ N, each fixed finite automaton A, and each finite automaton B given at the input, the problem of determining the existence of a diverse set {w_1 , w_2 , . . . , w_r } ⊆ L(B) of words that are synchronizing for A can be solved in polynomial time. This result yields new applications of the notion of synchronization to the subfields of artificial intelligence mentioned above.

Synchronization and Diversity of Solutions

We present a fully computer-assisted proof system for solving a particular family of problems in Extremal Combinatorics. Existing techniques using Flag Algebras have proven powerful in the past, but have so far lacked a computational counterpart to derive matching constructive bounds. We demonstrate that common search heuristics are capable of finding constructions far beyond the reach of human intuition. Additionally, the most obvious downside of such heuristics, namely a missing guarantee of global optimality, can often be fully eliminated in this case through lower bounds and stability results coming from the Flag Algebra approach.

To illustrate the potential of this approach, we study two related and well-known problems in Extremal Graph Theory that go back to questions of Erd\H{o}s from the 60s.
Most notably, we present the first major improvement in the upper bound of the Ramsey multiplicity of $K_4$ in 25 years, precisely determine the first off-diagonal Ramsey multiplicity number, and settle the minimum number of independent sets of size four in graphs with clique number strictly less than five.

Fully Computer-Assisted Proofs in Extremal Combinatorics

A critical challenge for open-domain dialogue agents is to generate persona-relevant and consistent responses. Due to the nature of persona sparsity in conversation scenarios, previous persona-based dialogue agents trained with Maximum Likelihood Estimation tend to overlook the given personas and generate responses irrelevant or inconsistent with personas. To address this problem, we propose a two-stage coarse-to-fine persona-aware training framework to improve the persona consistency of a dialogue agent progressively. Specifically, our framework first trains the dialogue agent to answer the constructed persona-aware questions, making it highly sensitive to the personas to generate persona-relevant responses. Then the dialogue agent is further trained with a contrastive learning paradigm by explicitly perceiving the difference between the consistent and the generated inconsistent responses, forcing it to pay more attention to the key persona information to generate consistent responses. By applying our proposed training framework to several representative baseline models, experimental results show significant boosts on both automatic and human evaluation metrics, especially the consistency of generated responses.

Learning to Know Myself: A Coarse-to-Fine Persona-aware Training Framework for Personalized Dialogue Generation

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construc- tion is time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. We introduce Reinforcement Learning Optimising Shaping Algorithm (ROSA), an automated reward shaping framework in which the shaping-reward function is constructed in a Markov game between two agents. A reward-shaping agent (Shaper) uses switching controls to determine which states to add shaping rewards for more efficient learning while the other agent (Controller) learns the optimal policy for the task using these shaped rewards. We prove that ROSA, which adopts existing RL algorithms, learns to construct a shaping-reward function that is beneficial to the task thus ensuring efficient convergence to high performance policies. We demonstrate ROSA’s properties in three didactic experiments and show its superior performance against state-of-the-art RS algorithms in challenging sparse reward environments.

Learning to Shape Rewards using a Game of Two Partners

Dynamic heterogeneous graph neural networks (DHGNNs) have been shown to be effective in handling the ubiquitous dynamic heterogeneous graphs. However, the existing DHGNNs are hand-designed, requiring extensive human efforts and failing to adapt to diverse dynamic heterogeneous graph scenarios. In this paper, we propose to automate the design of DHGNN, which faces two major challenges: 1) how to design the search space to jointly consider the spatial-temporal dependencies and heterogeneous interactions in graphs; 2) how to design an efficient search algorithm in the potentially large and complex search space. To tackle these challenges, we propose a novel Dynamic Heterogeneous Graph Attention Search (DHGAS) method. Our proposed method can automatically discover the optimal DHGNN architecture and adapt to various dynamic heterogeneous graph scenarios without human guidance. In particular, we first propose a unified dynamic heterogeneous graph attention (DHGA) framework, which enables each node to jointly attend its heterogeneous and dynamic neighbors. Based on the framework, we design a localization space to determine where the attention should be applied and a parameterization space to determine how the attention should be parameterized. Lastly, we design a multi-stage differentiable search algorithm to efficiently explore the search space. Extensive experiments on real-world dynamic heterogeneous graph datasets demonstrate that our proposed method significantly outperforms state-of-the-art baselines for tasks including link prediction, node classification and node regression. To the best of our knowledge, DHGAS is the first dynamic heterogeneous graph neural architecture search method.

Premium content

Unsupervised Multi-exposure Image Fusion Breaking Exposure Limits via Contrastive Learning

Downloads

Next from AAAI 2023

Multi-Stage Facility Location Problems with Transient Agents

Similar lecture

MCL: Multi-Granularity Contrastive Learning Framework for Chinese NER