Self-supervised learning, or SSL, holds the key to expanding the usage of machine learning in real-world tasks by alleviating heavy human supervision. Contrastive learning and its varieties have been SSL strategies in various fields. We use margins as a stepping stone for understanding how contrastive learning works at a deeper level and providing potential directions to improve representation learning. Through gradient analysis, we found that margins scale gradients in three different ways: emphasizing positive samples, de-emphasizing positive samples when angles of positive samples are wide, and attenuating the diminishing gradients as the estimated probability approaches the target probability. We separately analyze each and provide possible directions for improving SSL frameworks. Our experimental results demonstrate that these properties can contribute to acquiring better representations, which can enhance performance in both seen and unseen datasets.
In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human problem-solving, and introduce an object detection algorithm, the Push and Pull clustering method. This dual strategy enhances AI's ARC problem-solving skills and provides insights for AGI progression. Yet, our work reveals the need for advanced data collection tools, robust training datasets, and refined model structures. This study highlights potential improvements for Decision Transformers and propels future AGI research.
Musicians and audio engineers sculpt and transform their sounds by connecting multiple processors, forming an audio processing graph. However, most deep-learning methods overlook this real-world practice and assume fixed graph settings. To bridge this gap, we develop a system that reconstructs the entire graph from a given reference audio. We first generate a realistic graph-reference pair dataset and train a simple blind estimation system composed of a convolutional reference encoder and a transformer-based graph decoder. We apply our model to singing voice effects and drum mixing estimation tasks. Evaluation results show that our method can reconstruct complex signal routings, including multi-band processing and sidechaining.
Unmanned aerial vehicles (UAVs) are expected to be used extensively in the future for various applications, either as user equipment (UEs) connected to a cellular wireless network, or as an infrastructure extension of an existing wireless network to serve other UEs. Next generation wireless networks will consider the use of UAVs for joint communication and radar and/or as dedicated radars for various sensing applications. Increasing number of UAVs will naturally result in larger number of communication and/or radar links that may cause interference to nearby networks, exacerbated further by the higher likelihood of line-of-sight signal propagation from UAVs even to distant receivers. With all these, it is critical to study network coexistence of UAV-mounted base stations (BSs) and radar transceivers. In this paper, using stochastic geometry, we derive closed-form expressions to characterize the performance of coexisting UAV radar and communication networks for spectrum overlay multiple access (SOMA) and time-division multiple access (TDMA). We evaluate successful ranging probability (SRP) and the transmission capacity (TC) and compare the performance of TDMA and SOMA. Our results show that SOMA can outperform TDMA on both SRP and TC when the node density of active UAV-radars is larger than the node density of UAV-comms.
Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition, segmentation performance is limited in autonomous driving environments with a lot of contextual information perpendicular to the road surface, such as people, buildings, and general objects. In this paper, we propose an efficient feature fusion method, Feature Fusion with Different Norms (FFDN) that utilizes rich global context of multi-level scale and vertical pooling module before self-attention that preserves most contextual information while reducing the complexity of global context encoding in the vertical direction. By doing this, we could handle the properties of representation in global space and reduce additional computational cost. In addition, we analyze low performance in challenging cases including small and vertically featured objects. We achieve the mean Interaction of-union(mIoU) of 73.1 and the Frame Per Second(FPS) of 191, which are comparable results with state-of-the-arts on Cityscapes test datasets.
The autonomous car must recognize the driving environment quickly for safe driving. As the Light Detection And Range (LiDAR) sensor is widely used in the autonomous car, fast semantic segmentation of LiDAR point cloud, which is the point-wise classification of the point cloud within the sensor framerate, has attracted attention in recognition of the driving environment. Although the voxel and fusion-based semantic segmentation models are the state-of-the-art model in point cloud semantic segmentation recently, their real-time performance suffer from high computational load due to high voxel resolution. In this paper, we propose the fast voxel-based semantic segmentation model using Point Convolution and 3D Sparse Convolution (PCSCNet). The proposed model is designed to outperform at both high and low voxel resolution using point convolution-based feature extraction. Moreover, the proposed model accelerates the feature propagation using 3D sparse convolution after the feature extraction. The experimental results demonstrate that the proposed model outperforms the state-of-the-art real-time models in semantic segmentation of SemanticKITTI and nuScenes, and achieves the real-time performance in LiDAR point cloud inference.
Energy harvesting offers an attractive and promising mechanism to power low-energy devices. However, it alone is insufficient to enable an energy-neutral operation, which can eliminate tedious battery charging and replacement requirements. Achieving an energy-neutral operation is challenging since the uncertainties in harvested energy undermine the quality of service requirements. To address this challenge, we present a rollout-based runtime energy-allocation framework that optimizes the utility of the target device under energy constraints. The proposed framework uses an efficient iterative algorithm to compute initial energy allocations at the beginning of a day. The initial allocations are then corrected at every interval to compensate for the deviations from the expected energy harvesting pattern. We evaluate this framework using solar and motion energy harvesting modalities and American Time Use Survey data from 4772 different users. Compared to state-of-the-art techniques, the proposed framework achieves 34.6% higher utility even under energy-limited scenarios. Moreover, measurements on a wearable device prototype show that the proposed framework has less than 0.1% energy overhead compared to iterative approaches with a negligible loss in utility.