United States

Event cameras asynchronously output the polarity values of pixel-level log intensity alterations. They are robust against motion blur and can be adopted in challenging light conditions. Owing to these advantages, event cameras have been employed in various vision tasks such as depth estimation, visual odometry, and object detection. In particular, event cameras are effective in stereo depth estimation to ï¬nd correspondence points between two cameras under challenging illumination conditions and/or fast motion. However, because event cameras provide spatially sparse event stream data, it is difï¬cult to obtain a dense disparity map. Although it is possible to estimate disparity from event data at the edge of a structure where intensity changes are likely to occur, estimating the disparity in a region where event occurs rarely is challenging. In this study, we propose a deep network that combines the features of an image with the features of an event to generate a dense disparity map. The proposed network uses images to obtain spatially dense features that are lacking in events. In addition, we propose a spatial multi-scale correlation between two fused feature maps for an accurate disparity map. To validate our method, we conducted experiments using synthetic and real-world datasets.

AAAI 2022

Event-Image Fusion Stereo Using Cross-Modality Feature Propagation

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

technical paper

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primarily on textual inputs. In this work, we demonstrate the feasibility of performing grounded language acquisition on paired visual percepts and raw speech inputs. This will allow human-robot interactions in which language about novel tasks and environments is learned from end-users, reducing dependence on textual inputs and potentially mitigating the effects of demographic bias found in widely available speech recognition systems. We leverage recent work in self-supervised speech representation models and show that learned representations of speech can make language grounding systems more inclusive towards specific groups while maintaining or even increasing general performance.

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

We develop new adaptive algorithms for variational inequalities with monotone operators, which capture many problems of interest, notably convex optimization and convex-concave saddle point problems. Our algorithms automatically adapt to unknown problem parameters such as the smoothness and the norm of the operator, and the variance of the stochastic evaluation oracle. We show that our algorithms are universal and simultaneously achieve the optimal convergence rates in the non-smooth, smooth, and stochastic settings. The convergence guarantees of our algorithms improve over existing adaptive methods and match the optimal non-adaptive algorithms. Additionally, prior works require that the optimization domain is bounded. In this work, we remove this restriction and give algorithms for unbounded domains that are adaptive and universal. Our general proof techniques can be used for many variants of the algorithm using one or two operator evaluations per iteration. The classical methods based on the ExtraGradient/MirrorProx algorithm require two operator evaluations per iteration, which is the dominant factor in the running time in many settings.

Adaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence

Ontology alignment (a.k.a ontology matching (OM)) plays a critical role in knowledge integration. Owing to the success of machine learning in many domains, it has been applied in OM. However, the existing methods, which often adopt ad-hoc feature engineering or non-contextual word embeddings, have not yet outperformed rule-based systems especially in an unsupervised setting. In this paper, we propose a novel OM system named BERTMap which can support both unsupervised and semi-supervised settings. It first predicts mappings using a classifier based on fine-tuning the contextual embedding model BERT on text semantics corpora extracted from ontologies, and then refines the mappings through extension and repair by utilizing the ontology structure and logic. Our evaluation with three alignment tasks on biomedical ontologies demonstrates that BERTMap can often perform better than the leading OM systems LogMap and AML.

BERTMap: A BERT-Based Ontology Alignment System

Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of interest might only exist in arbitrary clips of untrimmed web videos, resulting in high label noises in the temporal space. To address this challenge, we introduce a new method for pre-training video action recognition models using queried web videos. Instead of trying to filter out potential noises, we propose to provide fine-grained supervision signals by defining the concept of Sub-Pseudo Label (SPL). Specifically, SPL spans out a new set of meaningful "middle ground" label space constructed by extrapolating the original weak labels during video querying and the prior knowledge distilled from a teacher model. Consequently, SPL provides enriched supervision for video models to learn better representations and improves data utilization efficiency of untrimmed videos. We validate the effectiveness of our method on four video action recognition datasets and a weakly-labeled image dataset. Experiments show that SPL outperforms several existing pre-training strategies and the learned representations lead to competitive results on several benchmarks.

Learning from Weakly-Labeled Web Videos via Exploring Sub-Concepts

Paraphrase generation is a fundamental and long-standing task in natural language processing. In this paper, we concentrate on two contributions to the task: (1) we propose Retrieval Augmented Prompt Tuning (RAPT) as a parameter-efficient method to adapt large pre-trained language models for paraphrase generation; (2) we propose Novelty Conditioned RAPT (NC-RAPT) as a simple model-agnostic method of using specialized prompt tokens for controlled paraphrase generation with varying levels of lexical novelty. By conducting extensive experiments on four datasets, we demonstrate the effectiveness of the proposed approaches for retaining the semantic content of the original text while inducing lexical novelty in the generation.

Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning

Multilingual neural machine translation (MNMT) aims to translate multiple languages with a single model and has been proved successful thanks to effective knowledge transfer among different languages with shared parameters. However, it is still an open question which parameters should be shared and which ones need to be task-specific. Currently, the common practice is to heuristically design or search language-specific modules, which is difficult to find the optimal configuration. In this paper, we propose a novel parameter differentiation based method that allows the model to determine which parameters should be language-speciï¬c during training. Inspired by cellular differentiation, each shared parameter in our method can dynamically differentiate into more specialized types. We further deï¬ne the differentiation criterion as inter-task gradient similarity. Therefore, parameters with conï¬‚icting inter-task gradients are more likely to be language-specific. Extensive experiments on multilingual datasets have demonstrated that our method signiï¬cantly outperforms various strong baselines with different parameter sharing conï¬gurations. Further analysis reveals that the parameter sharing configuration obtained by our method correlates well with the linguistic proximities.

Parameter Differentiation Based Multilingual Neural Machine Translation

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training which follows two stepsâ€”collecting adversarial examples by attacking a target model, and fine-tuning the model on the augmented dataset with these adversarial examples. The objective of traditional adversarial training is to make a model produce the same correct predictions on an original/adversarial example pair. However, the consistency between model decision-makings on two similar texts is ignored. We argue that a robust model should behave consistently on original/adversarial example pairs, that is making the same predictions (what) based on the same reasons (how) which can be reflected by consistent interpretations. In this work, we propose a novel feature-level adversarial training method named FLAT. FLAT aims at improving model robustness in terms of both predictions and interpretations. FLAT incorporates variational word masks in neural networks to learn global word importance and play as a bottleneck teaching the model to make predictions based on important words. FLAT explicitly shoots at the vulnerability problem caused by the mismatch between model understandings on the replaced words and their synonyms in original/adversarial example pairs by regularizing the corresponding global word importance scores. Experiments show the effectiveness of FLAT in improving the robustness with respect to both predictions and interpretations of four neural network models (LSTM, CNN, BERT, and DeBERTa) to two adversarial attacks on four text classification tasks. The models trained via FLAT also show better robustness than baseline models on unforeseen adversarial examples across different attacks.

Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation

Jan-ken, a.k.a. rock-paper-scissors, is a cerebrated example of a non-transitive game with three (pure) strategies, rock, paper and scissors. Interestingly, any Jan-ken generalized to four strategies contains at least one useless strategy unless it allows a tie between distinct pure strategies. Non-transitive dice could be a stochastic analogue of Jan-ken: the stochastic transitivity does not hold on some sets of dice, e.g., Efron's dice. Including the non-transitive dice, this paper is interested in dice sets which do not contain a useless die.
  In particular, we are concerned with the existence of a strongest (or weakest, symmetrically) die in a dice set under the two conditions that (1) any number appears on at most one die and at most one side, i.e., no tie break between two distinct dice, and (2) the mean pips of dice are the same. We firstly prove that a strongest die never exist if a set of n dice of m-sided is given as a partition of the set of numbers {1,â€¦,mn}. Next, we show some sufficient conditions that a strongest die exists in a dice set which is not a partition of a set of numbers. We also give some algorithms to find a strongest die in a dice set which includes given dice.

Is There a Strongest Die in a Set of Dice with the Same Mean Pips?

Non-Local Attention (NLA) brings significant improvement for Single Image Super-Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However, NLA gives noisy information large weights and consumes quadratic computation resources with respect to the input size, limiting its performance and application. In this paper, we propose a novel Efficient Non-Local Contrastive Attention (ENLCA) to perform long-range visual modeling and leverage more relevant non-local features. Specifically, ENLCA consists of two parts, Efficient Non-Local Attention (ENLA) and Sparse Aggregation. ENLA adopts the kernel method to approximate exponential function and obtains linear computation complexity. For Sparse Aggregation, we multiply inputs by an amplification factor to focus on informative features, yet the variance of approximation increases exponentially. Therefore, contrastive learning is applied to further separate relevant and irrelevant features. To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone. Extensive experimental results show that ENLCN reaches superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.

Efficient Non-Local Contrastive Attention for Image Super-Resolution

Multi-Agent Path Finding (MAPF) is the problem of finding a set of collision-free paths for a team of agents in a common environment. MAPF is NP-hard to solve optimally and, in some cases, also bounded-suboptimally. It is thus time-consuming for (bounded-sub)optimal solvers to solve large MAPF instances. Anytime algorithms find solutions quickly for large instances and then improve them to close-to-optimal ones over time. In this paper, we improve the current state-of-the-art anytime solver MAPF-LNS, that first finds an initial solution fast and then repeatedly replans the paths of subsets of agents via Large Neighborhood Search (LNS). It generates the subsets of agents for replanning by randomized destroy heuristics, but not all of them increase the solution quality substantially. We propose to use machine learning to learn how to select a subset of agents from a collection of subsets, such that replanning increases the solution quality more. We show experimentally that our solver, MAPF-ML-LNS, significantly outperforms MAPF-LNS on the standard MAPF benchmark set in terms of both the speed of improving the solution and the final solution quality.

Downloads

Next from AAAI 2022

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

Similar lecture

Deep Event Stereo Leveraged by Event-to-Image Translation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2022

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

Similar lecture

Deep Event Stereo Leveraged by Event-to-Image Translation

Downloads