Search Results for author:
Found 82 papers, 27 papers with code
Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Deep quantization methods have shown high efficiency on large-scale image retrieval.
Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
Our framework and model introduce the following key aspects: (1) to learn real-world adaptive semantic representation for objects with diverse and complex structures under real-world scenes, we introduce extra semantic segmentation and edge detection tasks on more diverse real-world data with segmentation annotations; (2) to avoid overfitting on low-level details, we propose a module to utilize the inconsistency between learned segmentation and matting representations to regularize detail refinement; (3) we propose a novel background line detection task into our auxiliary learning framework, to suppress interference of background lines or textures.
Invertible Diffusion Models for Compressed Sensing
To enable such memory-intensive end-to-end finetuning, we propose a novel two-level invertible design to transform both (1) the multi-step sampling process and (2) the noise estimation U-Net in each step into invertible networks.
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
This implies that our FedCEO can effectively recover the disrupted semantic information by smoothing the global semantic space for different privacy settings and continuous training processes.
Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
Model Inversion (MI) attacks aim to disclose private information about the training data by abusing access to the pre-trained models.
Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach
The transition from CPS-based Industry 4. 0 to CPSS-based Industry 5. 0 brings new requirements and opportunities to current sensing approaches, especially in light of recent progress in Chatbots and Large Language Models (LLMs).
Fast Implicit Neural Representation Image Codec in Resource-limited Devices
With different parameter settings, our method can outperform popular AE-based codecs in constrained environments in terms of both quality and decoding time, or achieve state-of-the-art reconstruction quality compared to other INR codecs.
MB-RACS: Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network
In this paper, we propose a Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network (MB-RACS) framework, which aims to adaptively determine the sampling rate for each image block in accordance with traditional measurement bounds theory.
FFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information
To address this limitation, we propose a Feature-based Fast Cascade Alignment network (FFCA-Net) to fully leverage the side information on the decoder.
Large Language Models in Medical Term Classification and Unexpected Misalignment Between Response and Reasoning
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3. 5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where the models' responses were misaligned with their reasoning.
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct.
Ranked #3 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 10-way (20-shot)
(using extra training data)
AdaptIR: Parameter Efficient Multi-task Adaptation for Pre-trained Image Restoration Models
Recently, Parameter Efficient Transfer Learning (PETL) offers an efficient alternative solution to full fine-tuning, yet still faces great challenges for pre-trained image restoration models, due to the diversity of different degradations.
Perceptual Image Compression with Cooperative Cross-Modal Side Information
The explosion of data has resulted in more and more associated text being transmitted along with images.
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression.
DAGC: Data-Volume-Aware Adaptive Sparsification Gradient Compression for Distributed Machine Learning in Mobile Computing
Assigning varying compression ratios to workers with distinct data distributions and volumes is thus a promising solution.
USDC: Unified Static and Dynamic Compression for Visual Transformer
To alleviate two disadvantages of two categories of methods, we propose to unify the static compression and dynamic compression techniques jointly to obtain an input-adaptive compressed model, which can further better balance the total compression ratios and the model performances.
ASP: Automatic Selection of Proxy dataset for efficient AutoML
Deep neural networks have gained great success due to the increasing amounts of data, and diverse effective neural network designs.
Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison
The success of ChatGPT has ignited an AI race, with researchers striving to develop new large language models (LLMs) that can match or surpass the language understanding and generation abilities of commercial ones.
KwaiYiiMath: Technical Report
Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning.
Ranked #87 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
MuseChat: A Conversational Music Recommendation System for Videos
The reasoning module, equipped with the power of Large Language Model (Vicuna-7B) and extended to multi-modal inputs, is able to provide reasonable explanation for the recommended music.
GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead.
Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling
Keyphrase generation is a task of identifying a set of phrases that best repre-sent the main topics or themes of a given text.
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.
Adjacency-hopping de Bruijn Sequences for Non-repetitive Coding
A special type of cyclic sequences named adjacency-hopping de Bruijn sequences is introduced in this paper.
Self-Supervised Scalable Deep Compressed Sensing
Compressed sensing (CS) is a promising tool for reducing sampling costs.
On the Performance of Multidimensional Constellation Shaping for Linear and Nonlinear Optical Fiber Channel
Multidimensional constellation shaping of up to 32 dimensions with different spectral efficiencies are compared through AWGN and fiber-optic simulations.
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.
Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks
We propose an improved end-to-end Minimax optimization method for this sparse learning problem to better balance the model performance and the computation efficiency.
One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition.
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability
Alternatively, model ensemble adversarial attacks are proposed to fuse outputs from surrogate models with diverse architectures to get an ensemble loss, making the generated adversarial example more likely to transfer to other models as it can fool multiple models concurrently.
Deep Physics-Guided Unrolling Generalization for Compressed Sensing
By absorbing the merits of both the model- and data-driven methods, deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction.
Mega-cities dominate China's urban greening
Trees play a crucial role in urban environments, offering various ecosystem services that contribute to public health and human well-being.
Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing
Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance.
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding
In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks.
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers
In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space.
Progressive Content-aware Coded Hyperspectral Compressive Imaging
Hyperspectral imaging plays a pivotal role in a wide range of applications, like remote sensing, medicine, and cytology.
Analytical Model of Nonlinear Fiber Propagation for General Dual-Polarization Four-Dimensional Modulation Format
As an application of our model, we further study the effects of signal-noise interactions in long-haul transmission via the proposed model.
Revisiting Image Deblurring with an Efficient ConvNet
In this work, we propose a unified lightweight CNN network that features a large effective receptive field (ERF) and demonstrates comparable or even better performance than Transformers while bearing less computational costs.
Ranked #2 on
Image Defocus Deblurring
on DPD
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Most in-the-wild images are stored in Low Dynamic Range (LDR) form, serving as a partial observation of the High Dynamic Range (HDR) visual world.
Contrastive Masked Autoencoders for Self-Supervised Video Hashing
To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames.
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years.
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain
Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.
Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compression
As a probabilistic modeling technique, the flow-based model has demonstrated remarkable potential in the field of lossless compression \cite{idf, idf++, lbb, ivpf, iflow},.
SIAD: Self-supervised Image Anomaly Detection System
To make a step forward, this paper outlines an automatic annotation system called SsaA, working in a self-supervised learning manner, for continuously making the online visual inspection in the manufacturing automation scenarios.
D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing
By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) for CS imaging with the capability of transmitting high-throughput feature-level image representation through all the unfolded stages.
Content-aware Scalable Deep Compressed Sensing
To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction.
Ranked #1 on
Image Compressed Sensing
on CBSD68
Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting
To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2.
Analytical SNR Prediction in Long-Haul Optical Transmission using General Dual-Polarization 4D Formats
Nonlinear interference models for dual-polarization 4D (DP-4D) modulation have only been used so far to predict signal-signal nonlinear interference.
Learning to Deblur using Light Field Generated and Real Defocus Images
We first train the network on a light field-generated dataset for its highly accurate image correspondence.
Ranked #1 on
Image Defocus Deblurring
on RealDOF
(using extra training data)
ViT-P: Rethinking Data-efficient Vision Transformers from Locality
We make vision transformers as data-efficient as convolutional neural networks by introducing multi-focal attention bias.
Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.
Subspace modeling for fast and high-sensitivity X-ray chemical imaging
Resolving morphological chemical phase transformations at the nanoscale is of vital importance to many scientific and industrial applications across various disciplines.
Shaped Four-Dimensional Modulation Formats for Optical Fiber Communication Systems
We review the design of multidimensional modulations by maximizing generalized mutual information and compare the maximum transmission reach of recently introduced 4D formats.
Low-Complexity Geometrical Shaping for 4D Modulation Formats via Amplitude Coding
Signal shaping is vital to approach Shannon's capacity, yet it is challenging to implement at very high speeds.
Model-aided Geometrical Shaping of Dual-polarization 4D Formats in the Nonlinear Fiber Channel
The geometry of dual-polarization four-dimensional constellations is optimized in the optical fiber channel using a recent nonlinear interference model.
Learning a self-supervised tone mapping operator via feature contrast masking loss
High Dynamic Range (HDR) content is becoming ubiquitous due to the rapid development of capture technologies.
Memory-Augmented Deep Unfolding Network for Compressive Sensing
By understanding DUNs from the perspective of the human brain's memory processing, we find there exists two issues in existing DUNs.
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
To this end, we propose the confusing perturbations-induced backdoor attack (CIBA).
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ).
Unbiased IoU for Spherical Image Object Detection
In this paper, we first identify that spherical rectangles are unbiased bounding boxes for objects in spherical images, and then propose an analytical method for IoU calculation without any approximations.
COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
In this paper, we propose a novel COntrollable Arbitrary-Sampling neTwork, dubbed COAST, to solve CS problems of arbitrary-sampling matrices (including unseen sampling matrices) with one single model.
Universal Adversarial Head: Practical Protection against Video Data Leakage
We propose $universal \ adversarial \ head$ (UAH), which crafts adversarial query videos by prepending the original videos with a sequence of adversarial frames to perturb the normal hash codes in the Hamming space.
MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph
Second, the contrastive scheme only learns representations that are invariant to local perturbations and thus does not consider the global structure of the dataset, which may also be useful for downstream tasks.
Shape-driven Coordinate Ordering for Star Glyph Sets via Reinforcement Learning
Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors to measure the perceptual distance between pairs of glyphs, and use the derived silhouette coefficient to measure the perception of class separability within the entire set.
Modeling of Nonlinear Interference Power for Dual-Polarization 4D Formats
We assess the accuracy of a recently introduced nonlinear interference model for general dual-polarization 4D formats.~ Unlike previous models for polarization-multiplexed 2D formats, an average gap from split-step Fourier simulations within 0. 1 dB is demonstrated.
Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection
However, universal language models may perform weakly in these fake news detection for lack of large-scale annotated data and sufficient semantic understanding of domain-specific knowledge.
Robust Collaborative Learning with Noisy Labels
In this paper, we study the underlying mechanism of how disagreement and agreement between networks can help reduce the noise in gradients and develop a novel framework called Robust Collaborative Learning (RCL) that leverages both disagreement and agreement among networks.
Dual Refinement Feature Pyramid Networks for Object Detection
SRB learns the location and content of sampling points based on contextual information between adjacent levels.
TAP-Net: Transport-and-Pack using Reinforcement Learning
Using a learning-based approach, a trained network can learn and encode solution patterns to guide the solution of new problem instances instead of executing an expensive online search.
Machine Learning in Heliophysics and Space Weather Forecasting: A White Paper of Findings and Recommendations
The authors of this white paper met on 16-17 January 2020 at the New Jersey Institute of Technology, Newark, NJ, for a 2-day workshop that brought together a group of heliophysicists, data providers, expert modelers, and computer/data scientists.
Targeted Attack for Deep Hashing based Retrieval
In this paper, we propose a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on such retrieval.
Analysis and Experimental Demonstration of Orthant-Symmetric Four-dimensional 7 bit/4D-sym Modulation for Optical Fiber Communication
We propose a new four-dimensional orthant-symmetric 128-ary modulation format (4D-OS128) with a spectral efficiency of 7bit/4D-sym.
Adversarial Attack on Deep Product Quantization Network for Image Retrieval
Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets.
End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information
GMI-based end-to-end learning is shown to be highly nonconvex.
The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective
Firstly, as there is a finite number of possibilities in the game, is there a quantifiable intelligence measurement for evaluating intelligent systems, e. g. AlphaZero?
An Unified Intelligence-Communication Model for Multi-Agent System Part-I: Overview
Motivated by Shannon's model and recent rehabilitation of self-supervised artificial intelligence having a "World Model", this paper propose an unified intelligence-communication (UIC) model for describing a single agent and any multi-agent system.
A Study of Deep Feature Fusion based Methods for Classifying Multi-lead ECG
An automatic classification method has been studied to effectively detect and recognize Electrocardiogram (ECG).
Aspects of Warped AdS$_3$/CFT$_2$ Correspondence
In this paper we apply the thermodynamics method to investigate the holographic pictures for the BTZ black hole, the spacelike and the null warped black holes in three-dimensional topologically massive gravity (TMG) and new massive gravity (NMG).
High Energy Physics - Theory General Relativity and Quantum Cosmology
