The sampling theorem plays a fundamental role for the recovery of continuous-time signals from discrete-time samples in the field of signal processing. The sampling theorem of non-band-limited signals has evolved into one of the most challenging problems. In this work, a generalized sampling theorem -- which builds on the Koopman operator -- is proved for signals in generator-bounded space (Theorem 1). It naturally extends the Nyquist-Shannon sampling theorem that, 1) for band-limited signals, the lower bounds of sampling frequency given by these two theorems are exactly the same; 2) the Koopman operator-based sampling theorem can also provide finite bound of sampling frequency for certain types of non-band-limited signals, which can not be addressed by Nyquist-Shannon sampling theorem. These types of non-band-limited signals include but not limited to, for example, inverse Laplace transform with limited imaginary interval of integration, and linear combinations of complex exponential functions. Moreover, the Koopman operator-based reconstruction algorithm is provided with theoretical result of convergence. By this algorithm, the sampling theorem is effectively illustrated on several signals related to sine, exponential and polynomial signals.
3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.
The images and sounds that we perceive undergo subtle but geometrically consistent changes as we rotate our heads. In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera rotation and localizing sound sources. We learn to solve these tasks solely through self-supervision. A visual model predicts camera rotation from a pair of images, while an audio model predicts the direction of sound sources from binaural sounds. We train these models to generate predictions that agree with one another. At test time, the models can be deployed independently. To obtain a feature representation that is well-suited to solving this challenging problem, we also propose a method for learning an audio-visual representation through cross-view binauralization: estimating binaural sound from one view, given images and sound from another. Our model can successfully estimate accurate rotations on both real and synthetic scenes, and localize sound sources with accuracy competitive with state-of-the-art self-supervised approaches. Project site: https://ificl.github.io/SLfM/
The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest. In addition to spatial-temporal correlations, the functionality of urban areas also plays a crucial role in traffic flow prediction. However, the exploration of regional functional attributes mainly focuses on adding additional topological structures, ignoring the influence of functional attributes on regional traffic patterns. Different from the existing works, we propose a novel module named POI-MetaBlock, which utilizes the functionality of each region (represented by Point of Interest distribution) as metadata to further mine different traffic characteristics in areas with different functions. Specifically, the proposed POI-MetaBlock employs a self-attention architecture and incorporates POI and time information to generate dynamic attention parameters for each region, which enables the model to fit different traffic patterns of various areas at different times. Furthermore, our lightweight POI-MetaBlock can be easily integrated into conventional traffic flow prediction models. Extensive experiments demonstrate that our module significantly improves the performance of traffic flow prediction and outperforms state-of-the-art methods that use metadata.
Many empirical studies have demonstrated the performance benefits of conditional computation in neural networks, including reduced inference time and power consumption. We study the fundamental limits of neural conditional computation from the perspective of memorization capacity. For Rectified Linear Unit (ReLU) networks without conditional computation, it is known that memorizing a collection of $n$ input-output relationships can be accomplished via a neural network with $O(\sqrt{n})$ neurons. Calculating the output of this neural network can be accomplished using $O(\sqrt{n})$ elementary arithmetic operations of additions, multiplications and comparisons for each input. Using a conditional ReLU network, we show that the same task can be accomplished using only $O(\log n)$ operations per input. This represents an almost exponential improvement as compared to networks without conditional computation. We also show that the $\Theta(\log n)$ rate is the best possible. Our achievability result utilizes a general methodology to synthesize a conditional network out of an unconditional network in a computationally-efficient manner, bridging the gap between unconditional and conditional architectures.
Federated learning has gained popularity as a solution to data availability and privacy challenges in machine learning. However, the aggregation process of local model updates to obtain a global model in federated learning is susceptible to malicious attacks, such as backdoor poisoning, label-flipping, and membership inference. Malicious users aim to sabotage the collaborative learning process by training the local model with malicious data. In this paper, we propose a novel robust aggregation approach based on recursive Euclidean distance calculation. Our approach measures the distance of the local models from the previous global model and assigns weights accordingly. Local models far away from the global model are assigned smaller weights to minimize the data poisoning effect during aggregation. Our experiments demonstrate that the proposed algorithm outperforms state-of-the-art algorithms by at least $5\%$ in accuracy while reducing time complexity by less than $55\%$. Our contribution is significant as it addresses the critical issue of malicious attacks in federated learning while improving the accuracy of the global model.
We introduce You Only Train Once (YOTO), a dynamic human generation framework, which performs free-viewpoint rendering of different human identities with distinct motions, via only one-time training from monocular videos. Most prior works for the task require individualized optimization for each input video that contains a distinct human identity, leading to a significant amount of time and resources for the deployment, thereby impeding the scalability and the overall application potential of the system. In this paper, we tackle this problem by proposing a set of learnable identity codes to expand the capability of the framework for multi-identity free-viewpoint rendering, and an effective pose-conditioned code query mechanism to finely model the pose-dependent non-rigid motions. YOTO optimizes neural radiance fields (NeRF) by utilizing designed identity codes to condition the model for learning various canonical T-pose appearances in a single shared volumetric representation. Besides, our joint learning of multiple identities within a unified model incidentally enables flexible motion transfer in high-quality photo-realistic renderings for all learned appearances. This capability expands its potential use in important applications, including Virtual Reality. We present extensive experimental results on ZJU-MoCap and PeopleSnapshot to clearly demonstrate the effectiveness of our proposed model. YOTO shows state-of-the-art performance on all evaluation metrics while showing significant benefits in training and inference efficiency as well as rendering quality. The code and model will be made publicly available soon.
Time delay neural network (TDNN) has been proven to be efficient for speaker verification. One of its successful variants, ECAPA-TDNN, achieved state-of-the-art performance at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses densely connected time delay neural network (D-TDNN) as backbone and adopts a novel multi-granularity pooling to capture contextual information at different levels. Extensive experiments on two public benchmarks, VoxCeleb and CN-Celeb, demonstrate that the proposed architecture outperforms other mainstream speaker verification systems with lower computational cost and faster inference speed.
Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the \textbf{Adaptive ColorMLP (AdaCM)}, an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.
Knowledge from diverse application domains is organized as knowledge graphs (KGs) that are stored in RDF engines accessible in the web via SPARQL endpoints. Expressing a well-formed SPARQL query requires information about the graph structure and the exact URIs of its components, which is impractical for the average user. Question answering (QA) systems assist by translating natural language questions to SPARQL. Existing QA systems are typically based on application-specific human-curated rules, or require prior information, expensive pre-processing and model adaptation for each targeted KG. Therefore, they are hard to generalize to a broad set of applications and KGs. In this paper, we propose KGQAn, a universal QA system that does not need to be tailored to each target KG. Instead of curated rules, KGQAn introduces a novel formalization of question understanding as a text generation problem to convert a question into an intermediate abstract representation via a neural sequence-to-sequence model. We also develop a just-in-time linker that maps at query time the abstract representation to a SPARQL query for a specific KG, using only the publicly accessible APIs and the existing indices of the RDF store, without requiring any pre-processing. Our experiments with several real KGs demonstrate that KGQAn is easily deployed and outperforms by a large margin the state-of-the-art in terms of quality of answers and processing time, especially for arbitrary KGs, unseen during the training.