Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning

Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards. To address this problem, recent approaches proposed to leverage intrinsic rewards to improve exploration, such as novelty-based exploration and prediction-based exploration. However, many intrinsic reward modules require sophisticated structures and representation learning, resulting in prohibitive computational complexity and unstable performance. In this paper, we propose Rewarding Episodic Visitation Discrepancy (REVD), a computation-efficient and quantified exploration method. More specifically, REVD provides intrinsic rewards by evaluating the R\'enyi divergence-based visitation discrepancy between episodes. To make efficient divergence estimation, a k-nearest neighbor estimator is utilized with a randomly-initialized state encoder. Finally, the REVD is tested on Atari games and PyBullet Robotics Environments. Extensive experiments demonstrate that REVD can significantly improves the sample efficiency of reinforcement learning algorithms and outperforms the benchmarking methods.

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as 'teachers' to develop a superior 'student' in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods. Code is available at https://github.com/xiaoachen98/DDB.git.

Aesthetics Driven Autonomous Time-Lapse Photography Generation by Virtual and Real Robots

Time-lapse photography is employed in movies and promotional films because it can reflect the passage of time in a short time and strengthen the visual attraction. However, since it takes a long time and requires the stable shooting, it is a great challenge for the photographer. In this article, we propose a time-lapse photography system with virtual and real robots. To help users shoot time-lapse videos efficiently, we first parameterize the time-lapse photography and propose a parameter optimization method. For different parameters, different aesthetic models, including image and video aesthetic quality assessment networks, are used to generate optimal parameters. Then we propose a time-lapse photography interface to facilitate users to view and adjust parameters and use virtual robots to conduct virtual photography in a three-dimensional scene. The system can also export the parameters and provide them to real robots so that the time-lapse videos can be filmed in the real world. In addition, we propose a time-lapse photography aesthetic assessment method that can automatically evaluate the aesthetic quality of time-lapse video. The experimental results show that our method can efficiently obtain the time-lapse videos. We also conduct a user study. The results show that our system has the similar effect as professional photographers and is more efficient.

Hierarchical Compositional Representations for Few-shot Action Recognition

Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction. However, few-shot action recognition has not been well explored and remains challenging because of data scarcity. In this paper, we propose a novel hierarchical compositional representations (HCR) learning approach for few-shot action recognition. Specifically, we divide a complicated action into several sub-actions by carefully designed hierarchical clustering and further decompose the sub-actions into more fine-grained spatially attentional sub-actions (SAS-actions). Although there exist large differences between base classes and novel classes, they can share similar patterns in sub-actions or SAS-actions. Furthermore, we adopt the Earth Mover's Distance in the transportation problem to measure the similarity between video samples in terms of sub-action representations. It computes the optimal matching flows between sub-actions as distance metric, which is favorable for comparing fine-grained patterns. Extensive experiments show our method achieves the state-of-the-art results on HMDB51, UCF101 and Kinetics datasets.

Underwater Ranker: Learn Which Is Better and How to Be Better

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. We will release our dataset and code.

Aesthetic Visual Question Answering of Photographs

Aesthetic assessment of images can be categorized into two main forms: numerical assessment and language assessment. Aesthetics caption of photographs is the only task of aesthetic language assessment that has been addressed. In this paper, we propose a new task of aesthetic language assessment: aesthetic visual question and answering (AVQA) of images. If we give a question of images aesthetics, model can predict the answer. We use images from \textit{www.flickr.com}. The objective QA pairs are generated by the proposed aesthetic attributes analysis algorithms. Moreover, we introduce subjective QA pairs that are converted from aesthetic numerical labels and sentiment analysis from large-scale pre-train models. We build the first aesthetic visual question answering dataset, AesVQA, that contains 72,168 high-quality images and 324,756 pairs of aesthetic questions. Two methods for adjusting the data distribution have been proposed and proved to improve the accuracy of existing models. This is the first work that both addresses the task of aesthetic VQA and introduces subjectiveness into VQA tasks. The experimental results reveal that our methods outperform other VQA models on this new task.

Aesthetic Language Guidance Generation of Images Using Attribute Comparison

With the vigorous development of mobile photography technology, major mobile phone manufacturers are scrambling to improve the shooting ability of equipments and the photo beautification algorithm of software. However, the improvement of intelligent equipments and algorithms cannot replace human subjective photography technology. In this paper, we propose the aesthetic language guidance of image (ALG). We divide ALG into ALG-T and ALG-I according to whether the guiding rules are based on photography templates or guidance images. Whether it is ALG-T or ALG-I, we guide photography from three attributes of color, lighting and composition of the images. The differences of the three attributes between the input images and the photography templates or the guidance images are described in natural language, which is aesthetic natural language guidance (ALG). Also, because of the differences in lighting and composition between landscape images and portrait images, we divide the input images into landscape images and portrait images. Both ALG-T and ALG-I conduct aesthetic language guidance respectively for the two types of input images (landscape images and portrait images).

Aesthetic Attributes Assessment of Images with AMANv2 and DPC-CaptionsV2

Image aesthetic quality assessment is popular during the last decade. Besides numerical assessment, nature language assessment (aesthetic captioning) has been proposed to describe the generally aesthetic impression of an image. In this paper, we propose aesthetic attribute assessment, which is the aesthetic attributes captioning, i.e., to assess the aesthetic attributes such as composition, lighting usage and color arrangement. It is a non-trivial task to label the comments of aesthetic attributes, which limit the scale of the corresponding datasets. We construct a novel dataset, named DPC-CaptionsV2, by a semi-automatic way. The knowledge is transferred from a small-scale dataset with full annotations to large-scale professional comments from a photography website. Images of DPC-CaptionsV2 contain comments up to 4 aesthetic attributes: composition, lighting, color, and subject. Then, we propose a new version of Aesthetic Multi-Attributes Networks (AMANv2) based on the BUTD model and the VLPSA model. AMANv2 fuses features of a mixture of small-scale PCCD dataset with full annotations and large-scale DPCCaptionsV2 dataset with full annotations. The experimental results of DPCCaptionsV2 show that our method can predict the comments on 4 aesthetic attributes, which are closer to aesthetic topics than those produced by the previous AMAN model. Through the evaluation criteria of image captioning, the specially designed AMANv2 model is better to the CNN-LSTM model and the AMAN model.

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones. Also, quite recently, there are architecture designs, which enable GAN to unsupervisedly learn the semantic attributes represented in different layers. However, there is still a lack of research on generating face images more consistent with human aesthetics. Based on EigenGAN [He et al., ICCV 2021], we build the techniques of reinforcement learning into the generator of EigenGAN. The agent tries to figure out how to alter the semantic attributes of the generated human faces towards more preferable ones. To accomplish this, we trained an aesthetics scoring model that can conduct facial beauty prediction. We also can utilize this scoring model to analyze the correlation between face attributes and aesthetics scores. Empirically, using off-the-shelf techniques from reinforcement learning would not work well. So instead, we present a new variant incorporating the ingredients emerging in the reinforcement learning communities in recent years. Compared to the original generated images, the adjusted ones show clear distinctions concerning various attributes. Experimental results using the MindSpore, show the effectiveness of the proposed method. Altered facial images are commonly more attractive, with significantly improved aesthetic levels.