AAAI 2024 论文列表

Artificial intelligence (AI) has immense potential in time series prediction, but most explainable tools have limited capabilities in providing a systematic understanding of important features over time. These tools typically rely on evaluating a single time point, overlook the time ordering of inputs, and neglect the time-sensitive nature of time series applications. These factors make it difficult for users, particularly those without domain knowledge, to comprehend AI model decisions and obtain meaningful explanations. We propose CGS-Mask, a post-hoc and model-agnostic cellular genetic strip mask-based saliency approach to address these challenges. CGS-Mask uses consecutive time steps as a cohesive entity to evaluate the impact of features on the final prediction, providing binary and sustained feature importance scores over time. Our algorithm optimizes the mask population iteratively to obtain the optimal mask in a reasonable time. We evaluated CGS-Mask on synthetic and real-world datasets, and it outperformed state-of-the-art methods in elucidating the importance of features over time. According to our pilot user study via a questionnaire survey, CGS-Mask is the most effective approach in presenting easily understandable time series prediction results, enabling users to comprehend the decision-making process of AI models with ease.

Few-shot semantic segmentation (FSS) aims to segment unseen objects in a query image using a few pixel-wise annotated support images, thus expanding the capabilities of semantic segmentation. The main challenge lies in extracting sufficient information from the limited support images to guide the segmentation process. Conventional methods typically address this problem by generating single or multiple prototypes from the support images and calculating their cosine similarity to the query image. However, these methods often fail to capture meaningful information for modeling the de facto joint distribution of pixel and category. Consequently, they result in incomplete segmentation of foreground objects and mis-segmentation of the complex background. To overcome this issue, we propose the Cross Gaussian Mixture Generative Model (CGMGM), a novel Gaussian Mixture Models~(GMMs)-based FSS method, which establishes the joint distribution of pixel and category in both the support and query images. Specifically, our method initially matches the feature representations of the query image with those of the support images to generate and refine an initial segmentation mask. It then employs GMMs to accurately model the joint distribution of foreground and background using the support masks and the initial segmentation mask. Subsequently, a parametric decoder utilizes the posterior probability of pixels in the query image, by applying the Bayesian theorem, to the joint distribution, to generate the final segmentation mask. Experimental results on PASCAL-5i and COCO-20i datasets demonstrate our CGMGM's effectiveness and superior performance compared to the state-of-the-art methods.

The click-based interactive segmentation aims to extract the object of interest from an image with the guidance of user clicks. Recent work has achieved great overall performance by employing feedback from the output. However, in most state-of-the-art approaches, 1) the inference stage involves inflexible heuristic rules and requires a separate refinement model, and 2) the number of user clicks and model performance cannot be balanced. To address the challenges, we propose a click-based and mask-guided interactive image segmentation framework containing three novel components: Cascade-Forward Refinement (CFR), Iterative Click Loss (ICL), and SUEM image augmentation. The CFR offers a unified inference framework to generate segmentation results in a coarse-to-fine manner. The proposed ICL allows model training to improve segmentation and reduce user interactions simultaneously. The proposed SUEM augmentation is a comprehensive way to create large and diverse training sets for interactive image segmentation. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach on five public datasets. Remarkably, our model reduces by 33.2%, and 15.5% the number of clicks required to surpass an IoU of 0.95 in the previous state-of-the-art approach on the Berkeley and DAVIS sets, respectively.

We present CFEVER, a Chinese dataset designed for Fact Extraction and VERification. CFEVER comprises 30,012 manually created claims based on content in Chinese Wikipedia. Each claim in CFEVER is labeled as “Supports”, “Refutes”, or “Not Enough Info” to depict its degree of factualness. Similar to the FEVER dataset, claims in the “Supports” and “Refutes” categories are also annotated with corresponding evidence sentences sourced from single or multiple pages in Chinese Wikipedia. Our labeled dataset holds a Fleiss’ kappa value of 0.7934 for five-way inter-annotator agreement. In addition, through the experiments with the state-of-the-art approaches developed on the FEVER dataset and a simple baseline for CFEVER, we demonstrate that our dataset is a new rigorous benchmark for factual extraction and verification, which can be further used for developing automated systems to alleviate human fact-checking efforts. CFEVER is available at https://ikmlab.github.io/CFEVER.

Neural Radiance Fields have demonstrated impressive performance in novel view synthesis. However, NeRF and most of its variants still rely on traditional complex pipelines to provide extrinsic and intrinsic camera parameters, such as COLMAP. Recent works, like NeRFmm, BARF, and L2G-NeRF, directly treat camera parameters as learnable and estimate them through differential volume rendering. However, these methods work for forward-looking scenes with slight motions and fail to tackle the rotation scenario in practice. To overcome this limitation, we propose a novel camera parameter free neural radiance field (CF-NeRF), which incrementally reconstructs 3D representations and recovers the camera parameters inspired by incremental structure from motion. Given a sequence of images, CF-NeRF estimates camera parameters of images one by one and reconstructs the scene through initialization, implicit localization, and implicit optimization. To evaluate our method, we use a challenging real-world dataset, NeRFBuster, which provides 12 scenes under complex trajectories. Results demonstrate that CF-NeRF is robust to rotation and achieves state-of-the-art results without providing prior information and constraints.

Bioinformatics has always been a prolific domain for generating complex satisfiability and optimization problems. For instance, the synthesis of multi-scale models of biological networks has recently been associated with the resolution of optimization problems mixing Boolean logic and universally quantified linear constraints (OPT+qLP), which can be benchmarked on real-world models. In this paper, we introduce a Counter-Example-Guided Abstraction Refinement (CEGAR) to solve such problems efficiently. Our CEGAR exploits monotone properties inherent to linear optimization in order to generalize counter-examples of Boolean relaxations. We implemented our approach by extending Answer Set Programming (ASP) solver Clingo with a quantified linear constraints propagator. Our prototype enables exploiting independence of sub-formulas to further exploit the generalization of counter-examples. We evaluate the impact of refinement and partitioning on two sets of OPT+qLP problems inspired by system biology. Additionally, we conducted a comparison with the state-of-the-art ASP solver Clingo[lpx] that handles non-quantified linear constraints, showing the advantage of our CEGAR approach for solving large problems.

Accurately computing optical flow in low-contrast and noisy dark images is challenging, especially when contour information is degraded or difficult to extract. This paper proposes CEDFlow, a latent space contour enhancement for estimating optical flow in dark environments. By leveraging spatial frequency feature decomposition, CEDFlow effectively encodes local and global motion features. Importantly, we introduce the 2nd-order Gaussian difference operation to select salient contour features in the latent space precisely. It is specifically designed for large-scale contour components essential in dark optical flow estimation. Experimental results on the FCDN and VBOF datasets demonstrate that CEDFlow outperforms state-of-the-art methods in terms of the EPE index and produces more accurate and robust flow estimation. Our code is available at: https://github.com/xautstuzfy.

Point cloud completion aims at completing shapes from their partial. Most existing methods utilized shape’s priors information for point cloud completion, such as inputting the partial and getting the complete one through an encoder-decoder deep learning structure. However, it is very often to easily cause the loss of information in the generation process because of the invisibility of missing areas. Unlike most existing methods directly inferring the missing points using shape priors, we address it as a cross-modality task. We propose a new Cross-modal Dual Phases Network (CDPNet) for shape completion. Our key idea is that the global information of the shape is obtained from the extra single-view image, and the partial point clouds provide the geometric information. After that, the multi-modal features jointly guide the specific structural information. To learn the geometric details of the shape, we chose to use patches to preserve the local geometric feature. In this way, we can generate shapes with enough geometric details. Experimental results show that our method achieves state-of-the-art performance on point cloud completion.

Autonomous driving systems rely on precise trajectory prediction for safe and efficient motion planning. Despite considerable efforts to enhance prediction accuracy, inherent uncertainties persist due to data noise and incomplete observations. Many strategies entail formalizing prediction outcomes into distributions and utilizing variance to represent uncertainty. However, our experimental investigation reveals that existing trajectory prediction models yield unreliable uncertainty estimates, necessitating additional customized calibration processes. On the other hand, directly applying current calibration techniques to prediction outputs may yield sub-optimal results due to using a universal scaler for all predictions and neglecting informative data cues. In this paper, we propose Customized Calibration Temperature with Regularizer (CCTR), a generic framework that calibrates the output distribution. Specifically, CCTR 1) employs a calibration-based regularizer to align output variance with the discrepancy between prediction and ground truth and 2) generates a tailor-made temperature scaler for each prediction using a post-processing network guided by context and historical information. Extensive evaluation involving multiple prediction and planning methods demonstrates the superiority of CCTR over existing calibration algorithms and uncertainty-aware methods, with significant improvements of 11%-22% in calibration quality and 17%-46% in motion planning.

Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our CAVEN agent can engage in fully-bidirectional natural language conversations by producing relevant questions and interpret free-form, potentially noisy responses from the oracle based on the audio-visual context. To enable such a capability, CAVEN is equipped with: i) a trajectory forecasting network that is grounded in audio-visual cues to produce a potential trajectory to the estimated goal, and (ii) a natural language based question generation and reasoning network to pose an interactive question to the oracle or interpret the oracle's response to produce navigation instructions. To train the interactive modules, we present a large scale dataset: AVN-Instruct, based on the Landmark-RxR dataset. To substantiate the usefulness of conversations, we present experiments on the benchmark audio-goal task using the SoundSpaces simulator under various noisy settings. Our results reveal that our fully-conversational approach leads to nearly an order-of-magnitude improvement in success rate, especially in localizing new sound sources and against methods that use only uni-directional interaction.

Detecting out-of-distribution (OOD) inputs is critical for reliable machine learning, but deep neural networks often make overconfident predictions, even for OOD inputs that deviate from the distribution of training data. Prior methods relied on the widely used softmax cross-entropy (CE) loss that is adequate for classifying in-distribution (ID) samples but not optimally designed for OOD detection. To address this issue, we propose CASE, a simple and effective OOD detection method by explicitly improving intra-class Compactness And inter-class Separability of feature Embeddings. To enhance the separation between ID and OOD samples, CASE uses a dual-loss framework, which includes a separability loss that maximizes the inter-class Euclidean distance to promote separability among different class centers, along with a compactness loss that minimizes the intra-class Euclidean distance to encourage samples to be close to their class centers. In particular, the class centers are defined as a free optimization parameter of the model and updated by gradient descent, which is simple and further enhances the OOD detection performance. Extensive experiments demonstrate the superiority of CASE, which reduces the average FPR95 by 37.11% and improves the average AUROC by 15.89% compared to the baseline method using a softmax confidence score on the more challenging CIFAR-100 model.

Multi-modal multi-label emotion recognition (MMER) aims to identify relevant emotions from multiple modalities. The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data. Recent studies are mainly devoted to exploring various fusion strategies to integrate multi-modal information into a unified representation for all labels. However, such a learning scheme not only overlooks the specificity of each modality but also fails to capture individual discriminative features for different labels. Moreover, dependencies of labels and modalities cannot be effectively modeled. To address these issues, this paper presents ContrAstive feature Reconstruction and AggregaTion (CARAT) for the MMER task. Specifically, we devise a reconstruction-based fusion mechanism to better model fine-grained modality-to-label dependencies by contrastively learning modal-separated and label-specific features. To further exploit the modality complementarity, we introduce a shuffle-based aggregation strategy to enrich co-occurrence collaboration among labels. Experiments on two benchmark datasets CMU-MOSEI and M3ED demonstrate the effectiveness of CARAT over state-of-the-art methods. Code is available at https://github.com/chengzju/CARAT.

Cross-Lingual Summarization (CLS) involves generating a summary for a given document in another language. Most of the existing approaches adopt multi-task training and knowledge distillation, which increases the training cost and improves the performance of CLS tasks intuitively but unexplainably. In this work, we propose Cross-Attention Reinforcement (CAR) module and incorporate the module into the transformer backbone to formulate the CAR-Transformer. The CAR module formulates a pseudo summarization policy parameterized by the cross-attention weights reinforced by the ground-truth monolingual summary without introducing extra model parameters. Our approach demonstrates more consistent improvement across CLS tasks compared to traditional multi-task training methods and outperforms the fine-tuned vanilla mBART by 3.67 and the best-performing multi-task training approach by 1.48 in ROUGE-L F1 score on the WikiLingua Korean-to-English CLS task.

Understanding the emotional polarity of multimodal content with metaphorical characteristics, such as memes, poses a significant challenge in Multimodal Emotion Recognition (MER). Previous MER researches have overlooked the phenomenon of metaphorical alignment in multimedia content, which involves non-literal associations between concepts to convey implicit emotional tones. Metaphor-agnostic MER methods may be misinformed by the isolated unimodal emotions, which are distinct from the real emotions blended in multimodal metaphors. Moreover, contextual semantics can further affect the emotions associated with similar metaphors, leading to the challenge of maintaining contextual compatibility. To address the issue of metaphorical alignment in MER, we propose to leverage a conditional generative approach for capturing metaphorical analogies. Our approach formulates schematic prompts and corresponding references based on theoretical foundations, which allows the model to better grasp metaphorical nuances. In order to maintain contextual sensitivity, we incorporate a disentangled contrastive matching mechanism, which undergoes curricular adjustment to regulate its intensity during the learning process. The automatic and human evaluation experiments on two benchmarks prove that, our model provides considerable and stable improvements in recognizing multimodal emotion with metaphor attributes.

We consider decentralized learning over a network of workers with heterogeneous datasets, in the presence of Byzantine workers. Byzantine workers may transmit arbitrary or malicious values to neighboring workers, leading to degradation in overall performance. The heterogeneous nature of the training data across various workers complicates the identification and mitigation of Byzantine workers. To address this complex problem, we introduce a resilient decentralized learning approach that combines the gradient descent algorithm with a novel robust aggregator. Specifically, we propose a remove-then-clip aggregator, whereby each benign worker meticulously filters the neighbors' values and subsequently projects the remaining values to a sphere centered at its local value, with an appropriately selected radius. We prove that our proposed method converges to a neighborhood of a stationary point for non-convex objectives under standard assumptions. Furthermore, empirical evaluations are provided to demonstrate the superior performance of our method in comparison to existing algorithms, under various Byzantine attack models.

Recently, Stitchable Neural Networks (SN-Net) is proposed to stitch some pre-trained networks for quickly building numerous networks with different complexity and performance trade-offs. In this way, the burdens of designing or training the variable-sized networks, which can be used in application scenarios with diverse resource constraints, are alleviated. However, SN-Net still faces a few challenges. 1) Stitching from multiple independently pre-trained anchors introduces high storage resource consumption. 2) SN-Net faces challenges to build smaller models for low resource constraints. 3). SN-Net uses an unlearned initialization method for stitch layers, limiting the final performance. To overcome these challenges, motivated by the recently proposed Learngene framework, we propose a novel method called Learngene Pool. Briefly, Learngene distills the critical knowledge from a large pre-trained model into a small part (termed as learngene) and then expands this small part into a few variable-sized models. In our proposed method, we distill one pre-trained large model into multiple small models whose network blocks are used as learngene instances to construct the learngene pool. Since only one large model is used, we do not need to store more large models as SN-Net and after distilling, smaller learngene instances can be created to build small models to satisfy low resource constraints. We also insert learnable transformation matrices between the instances to stitch them into variable-sized models to improve the performance of these models. Exhaustive experiments have been implemented and the results validate the effectiveness of the proposed Learngene Pool compared with SN-Net.

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and improves implicit modeling to train a high-fidelity causal dynamics model that can be reused for all tasks in the same environment. Empirical validation on two manipulation environments and four tasks reveals that CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones. Furthermore, the derived state abstractions allow a task learner to achieve near-oracle levels of sample efficiency and outperform baselines on all tasks.

We present a modular recommender system framework that tightly integrates yet maintains the independence of individual components, thus satisfying two of the most critical aspects of industrial applications, generality and specificity. On the one hand, we ensure that each component remains self-contained and is ready to serve in other applications beyond recommender systems. On the other hand, when these components are combined, a unified theme emerges for recommender systems. We present the details of each component in the context of recommender systems and other applications. We release each component as an open-source library, and most importantly, we release their integration under MAB2REC, an industry-strength open-source software for building bandit-based recommender systems. By bringing standalone components together, Mab2Rec realizes a powerful and scalable toolchain to build and deploy business-relevant personalization applications. Finally, we share our experience and best practices for user training, adoption, performance evaluation, deployment, and model governance within the enterprise and the broader community.

In the realm of business automation, digital assistants/chatbots are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through APIs and RPAs. To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the "build" phase to assist humans in creating skills for digital assistants. As a result, the system doesn't need to rely on LLMs during conversations with business users, leading to efficient deployment. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.