Abstract:Transformers have found extensive applications across various domains due to the powerful fitting capabilities. This success can be partially attributed to their inherent nonlinearity. Thus, in addition to the ReLU function employed in the original transformer architecture, researchers have explored alternative modules such as GeLU and SwishGLU to enhance nonlinearity and thereby augment representational capacity. In this paper, we propose a novel category of polynomial composition activations (PolyCom), designed to optimize the dynamics of transformers. Theoretically, we provide a comprehensive mathematical analysis of PolyCom, highlighting its enhanced expressivity and efficacy relative to other activation functions. Notably, we demonstrate that networks incorporating PolyCom achieve the $\textbf{optimal approximation rate}$, indicating that PolyCom networks require minimal parameters to approximate general smooth functions in Sobolev spaces. We conduct empirical experiments on the pre-training configurations of large language models (LLMs), including both dense and sparse architectures. By substituting conventional activation functions with PolyCom, we enable LLMs to capture higher-order interactions within the data, thus improving performance metrics in terms of accuracy and convergence rates. Extensive experimental results demonstrate the effectiveness of our method, showing substantial improvements over other activation functions. Code is available at https://github.com/BryceZhuo/PolyCom.
Abstract:In this paper, we propose an advanced approach in targeting the problem of monocular 3D lane detection by leveraging geometry structure underneath the process of 2D to 3D lane reconstruction. Inspired by previous methods, we first analyze the geometry heuristic between the 3D lane and its 2D representation on the ground and propose to impose explicit supervision based on the structure prior, which makes it achievable to build inter-lane and intra-lane relationships to facilitate the reconstruction of 3D lanes from local to global. Second, to reduce the structure loss in 2D lane representation, we directly extract top view lane information from front view images, which tremendously eases the confusion of distant lane features in previous methods. Furthermore, we propose a novel task-specific data augmentation method by synthesizing new training data for both segmentation and reconstruction tasks in our pipeline, to counter the imbalanced data distribution of camera pose and ground slope to improve generalization on unseen data. Our work marks the first attempt to employ the geometry prior information into DNN-based 3D lane detection and makes it achievable for detecting lanes in an extra-long distance, doubling the original detection range. The proposed method can be smoothly adopted by other frameworks without extra costs. Experimental results show that our work outperforms state-of-the-art approaches by 3.8% F-Score on Apollo 3D synthetic dataset at real-time speed of 82 FPS without introducing extra parameters.
Abstract:Stereo visual odometry is widely used where a robot tracks its position and orientation using stereo cameras. Most of the approaches recovered mobile robotics motion based on the matching and tracking of point features along a sequence of stereo images. But in low-textured and dynamic scenes, there are no sufficient robust static point features for motion estimation, causing lots of previous work to fail to reconstruct the robotic motion. However, line features can be detected in such low-textured and dynamic scenes. In this paper, we proposed DynPL-SVO, a stereo visual odometry with the $dynamic$ $grid$ algorithm and the cost function containing both vertical and horizontal information of the line features. Stereo camera motion was obtained through Levenberg-Marquard minimization of re-projection error of point and line features. The experimental results on the KITTI and EuRoC MAV datasets showed that the DynPL-SVO had a competitive performance when compared to other state-of-the-art systems by producing more robust and accurate motion estimation, especially in low-textured and dynamic scenes.
Abstract:The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
Abstract:Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of these works use unified augmentation policies for all samples in a dataset, which is observed not necessarily beneficial for all labels in multi-label classification tasks, i.e., some policies may have negative impacts on some labels while benefitting the others. To tackle this problem, we propose a novel Label-Based AutoAugmentation (LB-Aug) method for multi-label scenarios, where augmentation policies are generated with respect to labels by an augmentation-policy network. The policies are learned via reinforcement learning using policy gradient methods, providing a mapping from instance labels to their optimal augmentation policies. Numerical experiments show that our LB-Aug outperforms previous state-of-the-art augmentation methods by large margins in multiple benchmarks on image and video classification.
Abstract:To make machine exhibit human-like abilities in the domains like robotics and conversation, social commonsense knowledge (SCK), i.e., common sense about social contexts and social roles, is absolutely necessarily. Therefor, our ultimate goal is to acquire large-scale SCK to support much more intelligent applications. Before that, we need to know clearly what is SCK and how to represent it, since automatic information processing requires data and knowledge are organized in structured and semantically related ways. For this reason, in this paper, we identify and formalize three basic types of SCK based on first-order theory. Firstly, we identify and formalize the interrelationships, such as having-role and having-social_relation, among social contexts, roles and players from the perspective of considering both contexts and roles as first-order citizens and not generating role instances. Secondly, we provide a four level structure to identify and formalize the intrinsic information, such as events and desires, of social contexts, roles and players, and illustrate the way of harvesting the intrinsic information of social contexts and roles from the exhibition of players in concrete contexts. And thirdly, enlightened by some observations of actual contexts, we further introduce and formalize the embedding of social contexts, and depict the way of excavating the intrinsic information of social contexts and roles from the embedded smaller and simpler contexts. The results of this paper lay the foundation not only for formalizing much more complex SCK but also for acquiring these three basic types of SCK.
Abstract:Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects. Firstly, we model the label correlations by superimposing label graph built from statistical co-occurrence information into the graph constructed from knowledge priors of labels, and then multi-layer graph convolutions are applied on the final superimposed graph for label embedding abstraction. Secondly, we propose to leverage embedding of the whole label system for better representation learning. In detail, lateral connections between GCN and CNN are added at shallow, middle and deep layers to inject information of label system into backbone CNN for label-awareness in the feature learning process. Extensive experiments are carried out on MS-COCO and Charades datasets, showing that our proposed solution can greatly improve the recognition performance and achieves new state-of-the-art recognition performance.