Searcharxiv⌕ Search

arXiv subjects

Kai Kang

Publications and source records attributed to Kai Kang.

At least 37 records · Page 2Linked to original sources
arXiv2024

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used LLMs. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled frames in an effective way. Specifically, the Slow pathway extracts features at a low frame rate while keeping as much spatial detail as possible (e.g., with 12x24 tokens), and the Fast pathway operates on a high frame rate but uses a larger spatial pooling stride (e.g., downsampling 6x) to focus on the motion cues. As a result, this design allows us to adequately capture both spatial and temporal features that are beneficial for detailed video understanding. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks. On some benchmarks, it achieves comparable or even better performance compared to state-of-the-art Video LLMs that are fine-tuned on video datasets. Code has been made available at: https://github.com/apple/ml-slowfast-llava.

cs.CV↗
arXiv2024

LMDX: Language Model-based Document Information Extraction and Localization

Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, their application in extracting information from visually rich documents, which is at the core of many document processing workflows and involving the extraction of key entities from semi-structured documents, has not yet been successful. The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechanism to localize the predicted entities within the document. In this paper, we introduce Language Model-based Document Information Extraction and Localization (LMDX), a methodology to reframe the document information extraction task for a LLM. LMDX enables extraction of singular, repeated, and hierarchical entities, both with and without training data, while providing grounding guarantees and localizing the entities within the document. Finally, we apply LMDX to the PaLM 2-S and Gemini Pro LLMs and evaluate it on VRDU and CORD benchmarks, setting a new state-of-the-art and showing how LMDX enables the creation of high quality, data-efficient parsers.

cs.CL↗
arXiv2024

Sharing Energy in Wide Area: A Two-Layer Energy Sharing Scheme for Massive Prosumers

The popularization of distributed energy resources transforms end-users from consumers into prosumers. Inspired by the sharing economy principle, energy sharing markets for prosumers are proposed to facilitate the utilization of renewable energy. This paper proposes a novel two-layer energy sharing market for massive prosumers, which can promote social efficiency by wider-area sharing. In this market, there is an upper-level wide-area market (WAM) in the distribution system and numerous lower-level local-area markets (LAMs) in communities. Prosumers in the same community share energy with each other in the LAM, which can be uncleared. The energy surplus and shortage of LAMs are cleared in the WAM. Thanks to the wide-area two-layer structure, the market outcome is near-social-optimal in large-scale systems. However, the proposed market forms a complex mathematical program with equilibrium constraints (MPEC). To solve the problem, we propose an efficient and hierarchically distributed bidding algorithm. The proposed two-layer market and bidding algorithm are verified on the IEEE 123-bus system with 11250 prosumers, which demonstrates the practicality and efficiency for large-scale markets.

cs.GT↗
arXiv2023

One-shot Learning for Channel Estimation in Massive MIMO Systems

In conventional supervised deep learning based channel estimation algorithms, a large number of training samples are required for offline training. However, in practical communication systems, it is difficult to obtain channel samples for every signal-to-noise ratio (SNR). Furthermore, the generalization ability of these deep neural networks (DNN) is typically poor. In this work, we propose a one-shot self-supervised learning framework for channel estimation in multi-input multi-output (MIMO) systems. The required number of samples for offline training is small and our approach can be directly deployed to adapt to variable channels. Our framework consists of a traditional channel estimation module and a denoising module. The denoising module is designed based on the one-shot learning method Self2Self and employs Bernoulli sampling to generate training labels. Besides,we further utilize a blind spot strategy and dropout technique to avoid overfitting. Simulation results show that the performance of the proposed one-shot self-supervised learning method is very close to the supervised learning approach while obtaining improved generalization ability for different channel environments.

eess.SP↗
arXiv2023

RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture

The techniques for 3D indoor scene capturing are widely used, but the meshes produced leave much to be desired. In this paper, we propose "RoomDreamer", which leverages powerful natural language to synthesize a new room with a different style. Unlike existing image synthesis methods, our work addresses the challenge of synthesizing both geometry and texture aligned to the input scene structure and prompt simultaneously. The key insight is that a scene should be treated as a whole, taking into account both scene texture and geometry. The proposed framework consists of two significant components: Geometry Guided Diffusion and Mesh Optimization. Geometry Guided Diffusion for 3D Scene guarantees the consistency of the scene style by applying the 2D prior to the entire scene simultaneously. Mesh Optimization improves the geometry and texture jointly and eliminates the artifacts in the scanned scene. To validate the proposed method, real indoor scenes scanned with smartphones are used for extensive experiments, through which the effectiveness of our method is demonstrated.

cs.CV↗
arXiv2022

Mixed-Timescale Deep-Unfolding for Joint Channel Estimation and Hybrid Beamforming

In massive multiple-input multiple-output (MIMO) systems, hybrid analog-digital beamforming is an essential technique for exploiting the potential array gain without using a dedicated radio frequency chain for each antenna. However, due to the large number of antennas, the conventional channel estimation and hybrid beamforming algorithms generally require high computational complexity and signaling overhead. In this work, we propose an end-to-end deep-unfolding neural network (NN) joint channel estimation and hybrid beamforming (JCEHB) algorithm to maximize the system sum rate in time-division duplex (TDD) massive MIMO. Specifically, the recursive least-squares (RLS) algorithm and stochastic successive convex approximation (SSCA) algorithm are unfolded for channel estimation and hybrid beamforming, respectively. In order to reduce the signaling overhead, we consider a mixed-timescale hybrid beamforming scheme, where the analog beamforming matrices are optimized based on the channel state information (CSI) statistics offline, while the digital beamforming matrices are designed at each time slot based on the estimated low-dimensional equivalent CSI matrices. We jointly train the analog beamformers together with the trainable parameters of the RLS and SSCA induced deep-unfolding NNs based on the CSI statistics offline. During data transmission, we estimate the low-dimensional equivalent CSI by the RLS induced deep-unfolding NN and update the digital beamformers. In addition, we propose a mixed-timescale deep-unfolding NN where the analog beamformers are optimized online, and extend the framework to frequency-division duplex (FDD) systems where channel feedback is considered. Simulation results show that the proposed algorithm can significantly outperform conventional algorithms with reduced computational complexity and signaling overhead.

cs.IT↗
arXiv2021

Computing Class Hierarchies from Classifiers

A class or taxonomic hierarchy is often manually constructed, and part of our knowledge about the world. In this paper, we propose a novel algorithm for automatically acquiring a class hierarchy from a classifier which is often a large neural network these days. The information that we need from a classifier is its confusion matrix which contains, for each pair of base classes, the number of errors the classifier makes by mistaking one for another. Our algorithm produces surprisingly good hierarchies for some well-known deep neural network models trained on the CIFAR-10 dataset, a neural network model for predicting the native language of a non-native English speaker, a neural network model for detecting the language of a written text, and a classifier for identifying music genre. In the literature, such class hierarchies have been used to provide interpretability to the neural networks. We also discuss some other potential uses of the acquired hierarchies.

cs.LG↗
arXiv2021

Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding

In this paper, we propose an end-to-end deep learning-based joint transceiver design algorithm for millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, which consists of deep neural network (DNN)-aided pilot training, channel feedback, and hybrid analog-digital (HAD) precoding. Specifically, we develop a DNN architecture that maps the received pilots into feedback bits at the receiver, and then further maps the feedback bits into the hybrid precoder at the transmitter. To reduce the signaling overhead and channel state information (CSI) mismatch caused by the transmission delay, a two-timescale DNN composed of a long-term DNN and a short-term DNN is developed. The analog precoders are designed by the long-term DNN based on the CSI statistics and updated once in a frame consisting of a number of time slots. In contrast, the digital precoders are optimized by the short-term DNN at each time slot based on the estimated low-dimensional equivalent CSI matrices. A two-timescale training method is also developed for the proposed DNN with a binary layer. We then analyze the generalization ability and signaling overhead for the proposed DNN based algorithm. Simulation results show that our proposed technique significantly outperforms conventional schemes in terms of bit-error rate performance with reduced signaling overhead and shorter pilot sequences.

cs.IT↗
arXiv2020

Fast Mitochondria Detection for Connectomics

High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since datasets can be petabytes in size. We present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL mitochondria benchmark. Our results show an Jaccard index of up to 0.90 with inference times lower than 16ms for a 512x512px image tile. This speed is faster than the acquisition speed of modern electron microscopes, enabling mitochondria detection in real-time. Our detector ranks first for real-time detection when compared to previous works and data, results, and code are openly available.

cs.CV↗
arXiv2017

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this work, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e. tubelets with convolutional neueral networks. The proposed framework won the recently introduced object-detection-from-video (VID) task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC2015).

cs.CV↗
arXiv2017

Object Detection in Videos with Tubelet Proposal Networks

Object detection in videos has drawn increasing attention recently with the introduction of the large-scale ImageNet VID dataset. Different from object detection in static images, temporal information in videos is vital for object detection. To fully utilize temporal information, state-of-the-art methods are based on spatiotemporal tubelets, which are essentially sequences of associated bounding boxes across time. However, the existing methods have major limitations in generating tubelets in terms of quality and efficiency. Motion-based methods are able to obtain dense tubelets efficiently, but the lengths are generally only several frames, which is not optimal for incorporating long-term temporal information. Appearance-based methods, usually involving generic object tracking, could generate long tubelets, but are usually computationally expensive. In this work, we propose a framework for object detection in videos, which consists of a novel tubelet proposal network to efficiently generate spatiotemporal proposals, and a Long Short-term Memory (LSTM) network that incorporates temporal information from tubelet proposals for achieving high object detection accuracy in videos. Experiments on the large-scale ImageNet VID dataset demonstrate the effectiveness of the proposed framework for object detection in videos.

cs.CV↗
arXiv2016

Pilot Decontamination via PDP Alignment

In this paper, we look into the issue of intra-cell uplink (UL) pilot orthogonalization and schemes for mitigating the inter-cell pilot contamination with a realistic massive multi-input multi-output (MIMO) orthogonal frequency-division multiplexing (OFDM) system model. First, we show how to align the power-delay profiles (PDP) of different users served by one BS so that the pilots sent within one common OFDM symbol are orthogonal. From the derived aligning rule, we see much more users can be sounded in the same OFDM symbol as their channels are sparse in time. Second, in the case of massive MIMO, we show how PDP alignment can help to alleviate the pilot contamination due to inter-cell interference. We demonstrate that, by utilizing the fact that different paths in time are associated with different angles of arrival (AoA), the pilot contamination can be significantly reduced through aligning the PDPs of the users served by different BSs appropriately. Computer simulations further convince us PDP aligning can serve as the new baseline design philosophy for the UL pilots in massive MIMO.

cs.IT↗
arXiv2016

Object Detection from Video Tubelets with Convolutional Neural Networks

Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. For object detection, particularly in still images, the performance has been significantly increased last year thanks to powerful deep networks (e.g. GoogleNet) and detection frameworks (e.g. Regions with CNN features (R-CNN)). The lately introduced ImageNet task on object detection from video (VID) brings the object detection task into the video domain, in which objects' locations at each frame are required to be annotated with bounding boxes. In this work, we introduce a complete framework for the VID task based on still-image object detection and general object tracking. Their relations and contributions in the VID task are thoroughly studied and evaluated. In addition, a temporal convolution network is proposed to incorporate temporal information to regularize the detection results and shows its effectiveness for the task.

cs.CV↗
arXiv2015

Can nano-particle melt below the melting temperature of its free surface partner?

The phonon thermal contribution to the melting temperature of nano-particles is inspected. The discrete summation of phonon states and its corresponding integration form as an approximation for a nano-particle or for a bulk system have been analyzed. The discrete phonon energy levels of pure size effect and the wave-vector shifts of boundary conditions were investigated in detail. Unlike in macroscopic thermodynamics, the integration volume of zero-mode of phonon for a nano-particle is not zero, and it plays an important role in pure size effect and boundary condition effect. We found that a nano-particle will have a rising melting temperature due to purely finite size effect; a lower melting temperature bound exists for a nano-particle in various environments, and the melting temperature of a nano-particle with free boundary condition reaches this lower bound. We suggest an easy procedure to estimation the melting temperature, in which the zero-mode contribution will be excluded, and only several bulk quantities will be used as input. We would like to emphasize that the quantum effect of discrete energy levels in nano-particles, which was not present in early thermodynamic studies on finite size corrections to melting temperature in small systems, should be included in future researches.

cond-mat.mes-hall↗
arXiv2014

Fully Convolutional Neural Networks for Crowd Segmentation

In this paper, we propose a fast fully convolutional neural network (FCNN) for crowd segmentation. By replacing the fully connected layers in CNN with 1 by 1 convolution kernels, FCNN takes whole images as inputs and directly outputs segmentation maps by one pass of forward propagation. It has the property of translation invariance like patch-by-patch scanning but with much lower computation cost. Once FCNN is learned, it can process input images of any sizes without warping them to a standard size. These attractive properties make it extendable to other general image segmentation problems. Based on FCNN, a multi-stage deep learning is proposed to integrate appearance and motion cues for crowd segmentation. Both appearance filters and motion filers are pretrained stage-by-stage and then jointly optimized. Different combination methods are investigated. The effectiveness of our approach and component-wise analysis are evaluated on two crowd segmentation datasets created by us, which include image frames from 235 and 11 scenes, respectively. They are currently the largest crowd segmentation datasets and will be released to the public.

cs.CV↗
arXiv2012

Zero Energy anomaly in one-dimensional Anderson lattice with exponentially correlated weak diadonal disorder

We calculated numerically the localization length of one-dimensional Anderson model with correlated diagonal disorder. For zero energy point in the weak disorder limit, we showed that the localization length changes continuously as the correlation of the disorder increases. We found that higher order terms of the correlation must be included into the current perturbation result in order to give the correct localization length, and to connect smoothly the anomaly at zero correlation with the perturbation result for large correlation.

cond-mat.dis-nn↗
arXiv2011

Unified description of perturbation theory and band center anomaly in one-dimensional Anderson localization

We calculated numerically the localization length of one-dimensional Anderson model with diagonal disorder. For weak disorder, we showed that the localization length changes continuously as the energy changes from the band center to the boundary of the anomalous region near the band edge. We found that all the localization lengths for different disorder strengths and different energies collapse onto a single curve, which can be fitted by a simple equation. Thus the description of the perturbation theory and the band center anomaly were unified into this equation.

cond-mat.dis-nn↗