United States

Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or negative, we investigate unlabeled imperfect expert demonstrations as they are. A positive-unlabeled adversarial imitation learning algorithm is developed to dynamically sample expert demonstrations that can well match the trajectories from the constantly optimized agent policy. The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations. Theoretical analysis shows that our method learns from the imperfect demonstrations via a self-paced way. Experimental results on MuJoCo and RoboSuite platforms demonstrate the effectiveness of our method from different aspects. 

AAAI 2023

Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning

gtep: imperfect information

ml: imitation learning & inverse reinforcement learning

gtep: adversarial 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

Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose tools from information theory that are able to naturally measure the statistical dependencies between random variables, thus they are usually of central interest in several statistical and machine learning tasks, such as conditional independence testing and representation learning. However, estimating CMI, or even MI, is infamously challenging due the intractable formulation. In this study, we introduce DINE (Diffeomorphic Information Neural Estimator)–a novel approach for estimating CMI of continuous random variables, inspired by the invariance of CMI over diffeomorphic maps. We show that the variables of interest can be replaced with appropriate surrogates that follow simpler distributions, allowing the CMI to be efficiently evaluated via analytical solutions. Additionally, we demonstrate the quality of the proposed estimator in comparison with state-of-the-arts in three important tasks, including estimating MI, CMI, as well as its application in conditional independence testing. The empirical evaluations show that DINE consistently outperforms competitors in all tasks and is able to adapt very well to complex and high-dimensional relationships.

Diffeomorphic Information Neural Estimation

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the model. We also show that input-specific saliency mapping is intrinsically susceptible to misleading feature attribution. Current attempts to use `general' input features for model interpretation assume  access to a dataset containing  those features, which biases the interpretation.  Addressing the gap, we introduce a new perspective of input-agnostic saliency mapping that computationally estimates the high-level  features attributed by the model to its outputs. These features are geometrically correlated, and are computed by accumulating model's gradient information with respect to an unrestricted data distribution. To compute these features, we nudge independent data points over the model loss surface towards the local minima associated by a human-understandable concept, e.g., class label for classifiers. With a systematic projection, scaling and refinement process, this information is transformed into an interpretable visualization without compromising its model-fidelity. The visualization serves as a stand-alone qualitative interpretation. With an extensive evaluation, we not only demonstrate successful visualizations for a variety of concepts for large-scale models, but also showcase an interesting utility of this new form of saliency mapping by identifying backdoor signatures in compromised classifiers.

Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers

The transferability of adversarial examples is the key property in practical black-box scenarios. Currently, numerous methods improve the transferability across different models trained on the same modality of data. The investigation of generating video adversarial examples with imagebased substitute models to attack the target video models, i.e., cross-modal transferability of adversarial examples, is rarely explored. A few works on cross-modal transferability directly apply image attack methods for each frame and no factors especial for video data are considered, which limits the cross-modal transferability of adversarial examples. In this paper, we propose an effective cross-modal attack method which considers both the global and local characteristics of video data. Firstly, from the global perspective, we introduce inter-frame interaction into attack process to induce more diverse and stronger gradients rather than perturb each frame separately. Secondly, from the local perspective, we disrupt the inherently local correlation of frames within a video, which prevents black-box video model from capturing valuable temporal clues. Extensive experiments on the UCF-101 and Kinetics-400 validate the proposed method significantly improves cross-modal transferability and even surpasses strong baseline using video models as substitute model. Our source codes are available at https://github.com/lwmming/Cross-Modal-Attack.

Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos

In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with both states and actions represented through a feature vector. The underlying structure of the environments allows the transition dynamics to be factored into two components: one that is environment-specific and another that is shared. Consider a set of environments that share the laws of motion as an example. In this setting, the agent can take a finite amount of reward-free interactions from a subset of these environments. The agent then must be able to approximately solve any planning task defined over any environment in the original set, relying on the above interactions only. Can we design a provably efficient algorithm that achieves this ambitious goal of systematic generalization? In this paper, we give a partially positive answer to this question. First, we provide a tractable formulation of systematic generalization by employing a causal viewpoint. Then, under specific structural assumptions, we provide a simple learning algorithm that guarantees any desired planning error up to an unavoidable sub-optimality term, while showcasing a polynomial sample complexity.

Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of adversarial examples, conventional adversarial attacks still generate traceable adversarial perturbations. In this paper, we introduce a novel Adversarial Attack via Invertible Neural Networks (AdvINN) method to produce robust and imperceptible adversarial examples. Specifically, AdvINN fully takes advantage of the information preservation property of Invertible Neural Networks and thereby generates adversarial examples by simultaneously adding class-specific semantic information of the target class and dropping discriminant information of the original class. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that the proposed AdvINN method can produce less imperceptible adversarial images than the state-of-the-art methods and AdvINN yields more robust adversarial examples with high confidence compared to other adversarial attacks.

Imperceptible Adversarial Attack via Invertible Neural Networks

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. 
However, existing knowledge distillation has side effects, such as propagating errors from the teacher to NAT students, which may limit further improvements of NAT models and are rarely discussed in existing research.
In this paper, we introduce selective knowledge distillation by introducing an NAT evaluator to select NAT-friendly targets that are of high quality and easy to learn.
In addition, we introduce a simple yet effective progressive distillation method to boost NAT performance. 
Experiment results on multiple WMT language directions and several representative NAT models show that our approach can realize a flexible trade-off between the quality and complexity of training data for NAT models, achieving strong performances.
Further analysis shows that distilling only 5% of the raw translations can help an NAT outperform its counterpart trained on raw data by about 2.4 BLEU.

Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation

Recent research showed that the dual-pixel sensor has made great progress in defocus map estimation and image defocus deblurring.
However, extracting real-time dual-pixel views is troublesome and complex in algorithm deployment.
Moreover, the deblurred image generated by the defocus deblurring network lacks high-frequency details, which is unsatisfactory in human perception. To overcome this issue, we propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring.
The proposed method consists of a learnable blur kernel to estimate the defocus map, which is an unsupervised method, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time.
The proposed network can learn the deblurring of different regions and recover realistic details. We propose a defocus adversarial loss to guide this training process.
Competitive experimental results confirm that with a learnable blur kernel, the generated defocus map can achieve results comparable to supervised methods.
In the single-image defocus deblurring task, the proposed method achieves state-of-the-art results, especially significant improvements in perceptual quality, where PSNR reaches 25.56 dB and LPIPS reaches 0.111.

Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild

In this paper, we study the problem of visual grounding by considering both phrase extraction and grounding (PEG). In contrast to the previous phrase-known-at-test setting, PEG requires a model to extract phrases from text and locate objects from image simultaneously, which is a more practical setting in real applications. As phrase extraction can be regarded as a $1$D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask prediction. Each pair of dual queries are designed to have shared positional parts but different content parts. Such a design effectively alleviates the difficulty of modality alignment between image and text (in contrast to a single query design) and empowers Transformer decoder to leverage phrase mask-guided attention to improve the performance. To evaluate the performance of PEG, we also propose a new metric CMAP (cross-modal average precision), analogous to the AP metric in object detection. The new metric overcomes the ambiguity of Recall@1 in many-box-to-one-phrase cases in phrase grounding. As a result, our PEG pre-trained DQ-DETR establishes new state-of-the-art results on all visual grounding benchmarks with a ResNet-101 backbone. For example, it achieves $91.04\%$ and $83.51\%$ in terms of recall rate on RefCOCO testA and testB with a ResNet-101 backbone. We will release the code after the blind review.

DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding

Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image. Thanks to the nature of the message passing neural network (MPNN) that models high-order interactions between objects and their neighboring objects, they are dominant representation learning modules for SGG. However, existing MPNN-based frameworks assume the scene graph as a homogeneous graph, which restricts the context-awareness of visual relations between objects. That is, they overlook the fact that the relations tend to be highly dependent on the objects with which the relations are associated. In this paper, we propose an unbiased heterogeneous scene graph generation (HetSGG) framework that captures relation-aware context using message passing neural networks. We devise a novel message passing layer, called relation-aware message passing neural network (RMP), that aggregates the contextual information of an image considering the predicate type of given objects. Our extensive evaluations demonstrate that HetSGG outperforms state-of-the-art methods, especially outperforming on tail predicate classes.

Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network

In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the few-shot learning (FSL) methods to leverage the low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain. We found that the local features are insufficient to FS-UDA, which could introduce noise or bias against classification, and not be used to effectively align the domains. To address the above issues, we aim to refine the local features to be more discriminative and relevant to classification. Thus, we propose a novel task-specific semantic feature learning method (TSECS) for FS-UDA. TSECS learns high-level semantic features for image-to-class similarity measurement. Based on the high-level features, we design a cross-domain self-training strategy to leverage the few labeled samples in source domain to build the classifier in target domain. In addition, we minimize the KL divergence of the high-level feature distributions between source and target domains to shorten the distance of the samples between the two domains. Extensive experiments on DomainNet show that the proposed method significantly outperforms SOTA methods in FS-UDA by a large margin (i.e., ~10%).

Premium content

Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning

Downloads

Next from AAAI 2023

Diffeomorphic Information Neural Estimation

Similar lecture

Don't Predict Counterfactual Values, Predict Expected Values Instead