United States

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is ``YES&#39;&#39;, and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in ``off-policyness&#39;&#39;,  Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods.

AAAI 2023

The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure

stochastic optimization

machine learning

reinforcement 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.

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is ``YES'', and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in ``off-policyness'',  Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods.

poster

Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection is still an open question. In this work, we present Point-Teaching, a weakly- and semi-supervised object detection framework to fully utilize the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple data augmentation, named Point-Guided Copy-Paste, to reduce the impact of those unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes. In particular, Point-Teaching outperforms the previous best
method Group R-CNN by 3.1 AP with 5% fully label and 2.3 AP with 30% fully label on MS COCO dataset. We believe that our proposed framework can largely lower the bar of learning accurate object detectors and pave the way for its
broader applications.



Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations

Recent work has demonstrated that pretrained transformers are overconfident in text classification tasks, which can be calibrated by the famous post-hoc calibration method temperature scaling (TS). Character or word spelling mistakes are frequently encountered in real applications and greatly threaten transformer model safety. Research on calibration under noisy settings is rare, and we focus on this direction. Based on a toy experiment, we discover that TS performs poorly when the datasets are perturbed by slight noise, such as swapping the characters, which results in distribution shift. We further utilize two metrics, predictive uncertainty and maximum mean discrepancy (MMD), to measure the distribution shift between clean and noisy datasets, based on which we propose a simple yet effective transferable TS method for calibrating models dynamically. To evaluate the performance of the proposed methods under noisy settings, we construct a benchmark consisting of four noise types and five shift intensities based on the QNLI, AG-News, and Emotion tasks. Experimental results on the noisy benchmark show that (1) the metrics are effective in measuring distribution shift and (2) transferable TS can significantly decrease the expected calibration error (ECE) compared with the competitive baseline ensemble TS by approximately 46.09\%.

Transferable Post-hoc Calibration on Pretrained Transformers in Noisy Text Classification

Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real adverse weather images would deteriorate their performance. To alleviate this issue, our start point is to unsupervisedly transfer the knowledge from source clean domain to target degraded domain. Our key insight is that adverse weather does not change the intrinsic optical flow of the scene, but causes a significant difference for the warp error between clean and degraded images. In this work, we propose the first unsupervised framework for adverse weather optical flow via hierarchical motion-boundary adaptation. Specifically, we first employ image translation to construct the transformation relationship between clean and degraded domains. In motion adaptation, we utilize the flow consistency knowledge to align the cross-domain optical flows into a motion-invariance common space, where the optical flow from clean weather is used as the guidance-knowledge to obtain a preliminary optical flow for adverse weather. Furthermore, we leverage the warp error inconsistency which measures the motion misalignment of the boundary between the clean and degraded domains, and propose a joint intra- and inter-scene boundary contrastive adaptation to refine the motion boundary. The hierarchical motion and boundary adaptation jointly promotes optical flow in a unified framework. Extensive quantitative and qualitative experiments have been performed to verify the superiority of the proposed method.

Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow

Although existing multi-object tracking (MOT) algorithms have obtained competitive performance on various benchmarks, almost all of them train and validate models on the same domain. The domain generalization problem of MOT is hardly studied. To bridge this gap, we first draw the observation that the high-level information contained in natural language is domain invariant to different tracking domains. Based on this observation, we propose to introduce natural language representation into visual MOT models for boosting the domain generalization ability. However, it is infeasible to label every tracking target with a textual description. To tackle this problem, we design two modules, namely visual context prompting (VCP) and visual-language mixing (VLM). Specifically, VCP generates visual prompts based on the input frames. VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes. Through training models on MOT17 and validating them on MOT20, we observe that the pseudo textual descriptions generated by our proposed modules improve the generalization performance of query-based trackers by large margins.

Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation

In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection. Our work is based on a key observation – depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%.

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble methods are redundant. For instance, over 77% of samples in CIFAR-100 dataset can be correctly classified with only a single ResNet-18 model, which indicates that only around 23% of the samples need an ensemble of extra models. To this end, we propose an inference efficient ensemble learning method, to simultaneously optimize for effectiveness and efficiency in ensemble learning. More specifically, we regard ensemble of models as a sequential inference process and learn the optimal halting event for inference on a specific sample. At each timestep of the inference process, a common selector judges if the current ensemble has reached ensemble effectiveness and halt further inference, otherwise filters this challenging sample for the subsequent models to conduct more powerful ensemble. Both the base models and common selector are jointly optimized to dynamically adjust ensemble inference for different samples with various hardness, through the novel optimization goals including sequential ensemble boosting and computation saving. The experiments with different backbones on real-world datasets illustrate our method can bring up to 56% inference cost reduction while maintaining comparable performance to full ensemble, achieving significantly better ensemble utility than other baselines.

Towards Inference Efficient Deep Ensemble Learning

Predicting high-fidelity future human poses, from a historically observed sequence, is crucial for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on external datasets and then directly apply it to all test samples, emerge as the dominant solution to solve this issue. Despite encouraging progress, they remain non-optimal, as the unique properties (e.g., motion style, rhythm) of a specific sequence cannot be adapted. More generally, once encountering out-of-distributions, the predicted poses tend to be unreliable. Motivated by this observation, we propose a novel test-time adaptation framework that leverages two self-supervised auxiliary tasks to help the primary forecasting network adapt to the test sequence. In the testing phase, our model can adjust the model parameters by several gradient updates to improve the generation quality. However, due to catastrophic forgetting, both auxiliary tasks typically have a low ability to automatically present the desired positive incentives for the final prediction performance. For this reason, we also propose a meta-auxiliary learning scheme for better adaptation. Extensive experiments show that the proposed approach achieves higher accuracy and more realistic visualization.

Meta-Auxiliary Learning for Adaptive Human Pose Prediction

Spike camera, a new type of neuromorphic visual sensor that imitates the sampling mechanism of the primate fovea, can capture photons and output 40000 Hz binary spike streams. Benefiting from the asynchronous sampling mechanism, the spike camera can record fast-moving objects and clear images can be recovered from the spike stream at any specified timestamps without motion blurring. Despite these, due to the dense time sequence information of the discrete spike stream, it is not easy to directly apply the existing algorithms of traditional cameras to the spike camera. Therefore, it is necessary and interesting to explore a universally effective representation of dense spike streams to better fit various network architectures. In this paper, we propose to mine temporal-robust features of spikes in time-frequency space with wavelet transforms. We present a novel Wavelet-Guided Spike Enhancing (WGSE) paradigm consisting of three consecutive steps: multi-level wavelet transform, CNN-based learnable module, and inverse wavelet transform. With the assistance of WGSE, the new streaming representation of spikes can be learned. We demonstrate the effectiveness of WGSE on two downstream tasks, achieving state-of-the-art performance on the image reconstruction task and getting considerable performance on semantic segmentation. Furthermore, We build a new spike-based synthesized dataset for semantic segmentation. Code and Datasets are available at https://github.com/Leozhangjiyuan/WGSE-SpikeCamera.

Learning Temporal-ordered Representation for Spike Streams Based on Discrete Wavelet Transforms

We study a novel graph path planning problem for multiple agents that may crash at runtime, and block part of the workspace. In our setting, agents can detect neighboring crashed agents, and change followed paths at runtime. The objective is then to prepare a set of paths and switching rules for each agent, ensuring that all correct agents reach their destinations without collisions or deadlocks, despite unforeseen crashes of other agents. Such planning is attractive to build reliable multi-robot systems. We present problem formalization, theoretical analysis such as computational complexities, and how to solve this offline planning problem.


Fault-Tolerant Offline Multi-Agent Path Planning

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate discriminative representations via enhancing the mutually semantic similar regions of support and query pairs. However, it suffers from two problems: CNN structure produces inaccurate attention map based on local features, and mutually similar backgrounds cause distraction. To alleviate these problems, we design a novel SpatialFormer structure to generate more accurate attention regions based on global features. Different from the traditional Transformer modeling intrinsic instance-level similarity which causes accuracy degradation in FSL, our SpatialFormer explores the semantic-level similarity between pair inputs to boost the performance. Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction. Particularly, SFSA highlights the regions with same semantic information between pair features, and SFTA finds potential foreground object regions of novel feature that are similar to base categories. Extensive experiments show that our methods are effective and achieve new state-of-the-art results on few-shot classification benchmarks.

The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure

Downloads

Next from AAAI 2023

Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations

Similar lecture

On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation