Search Results for author:
Found 84 papers, 54 papers with code
Memory Efficient Transformer Adapter for Dense Predictions
While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e. g., standard normalization and frequent reshaping.
Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion
Theoretically, we have proved that the optimization direction of the image enhancement model will not be biased by the auxiliary visual recognition model under the implementation of GradProm.
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
For the first time, our model SnapGen, demonstrates the generation of 1024x1024 px images on a mobile device around 1. 4 seconds.
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
In this work, we re-formulate the model compression problem into the customized compensation problem: Given a compressed model, we aim to introduce residual low-rank paths to compensate for compression errors under customized requirements from users (e. g., tasks, compression ratios), resulting in greater flexibility in adjusting overall capacity without being constrained by specific compression formats.
Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection
To tackle these issues, we propose D2UE, a Diversified Dual-space Uncertainty Estimation framework for medical anomaly detection.
Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation
However, the limited availability of labeled foreground organs and the absence of supervision to distinguish unlabeled foreground organs from the background pose a significant challenge, which leads to a distribution mismatch between labeled and unlabeled pixels.
Aligning Medical Images with General Knowledge from Large Language Models
Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability.
Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation
To address this gap, we established a most comprehensive benchmark to evaluate the performance of off-the-shelf foundation models across six distinct clinical task types, encompassing a total of 39 specific tasks.
Non-parametric regularization for class imbalance federated medical image classification
Limited training data and severe class imbalance pose significant challenges to developing clinically robust deep learning models.
Dynamic neural network with memristive CIM and CAM for 2D and 3D vision
In contrast, AI models are static, unable to associate inputs with past experiences, and run on digital computers with physically separated memory and processing.
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs).
FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness
We begin by evaluating the completeness of annotations at the client level using a designed indicator.
FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity
Experiments on two publicly-available medical datasets validate the superiority of FedMLP against the state-of-the-art both federated semi-supervised and noisy label learning approaches under task heterogeneity.
Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver
We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4. 2-fold projected speedup and a 41. 4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin.
Efficient and accurate neural field reconstruction using resistive memory
The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
MedIAnomaly: A comparative study of anomaly detection in medical images
Anomaly detection (AD) aims at detecting abnormal samples that deviate from the expected normal patterns.
Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs.
SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts
Specifically, based on SAM, SAMCT is further equipped with a U-shaped CNN image encoder, a cross-branch interaction module, and a task-indicator prompt encoder.
Prompt-Guided Adaptive Model Transformation for Whole Slide Image Classification
To address this issue, we propose PAMT, a novel Prompt-guided Adaptive Model Transformation framework that enhances MIL classification performance by seamlessly adapting pre-trained models to the specific characteristics of histopathology data.
Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective
To the best of our knowledge, this is the first effort to theoretically clarify the principles and design philosophy of AE for anomaly detection.
Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification
In this paper, we introduce an Iterative Online Image Synthesis (IOIS) framework to address the class imbalance problem in medical image classification.
DoRA: Weight-Decomposed Low-Rank Adaptation
By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead.
Ranked #2 on
parameter-efficient fine-tuning
on WinoGrande
(using extra training data)
Towards Complementary Knowledge Distillation for Efficient Dense Image Prediction
In this work, we propose a complementary boundary and context distillation (BCD) method within the KD framework for EDIPs, which facilitates the targeted knowledge transfer from large accurate teacher models to compact efficient student models.
BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels
To alleviate this problem, in this paper, we propose a weakly-supervised nuclei segmentation method that only requires partial point labels of nuclei.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
In this work, we propose CoT-Influx, a novel approach that pushes the boundary of few-shot Chain-of-Thoughts (CoT) learning to improve LLM mathematical reasoning.
Ranked #113 on
Arithmetic Reasoning
on GSM8K
CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels
However, a major doubt about online learning is whether students are as engaged as they are in face-to-face classes.
Pruning random resistive memory for optimizing analogue AI
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63. 1 on the common sense zero-shot reasoning tasks, which is only 5. 8 lower than the full-precision model, significantly outperforming the previous state-of-the-art by 12. 7 points.
Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
A method for measuring the synthesis complexity is proposed to automatically determine the synthesis order in our sequential GAN.
Radiomics-Informed Deep Learning for Classification of Atrial Fibrillation Sub-Types from Left-Atrium CT Volumes
Furthermore, we ensure complementary information is learned by deep and radiomic features by designing a novel feature de-correlation loss.
A 137.5 TOPS/W SRAM Compute-in-Memory Macro with 9-b Memory Cell-Embedded ADCs and Signal Margin Enhancement Techniques for AI Edge Applications
In this paper, we propose a high-precision SRAM-based CIM macro that can perform 4x4-bit MAC operations and yield 9-bit signed output.
Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
We explore the best practices to alleviate the variation's influence during low-bit transformer QAT and propose a variation-aware quantization scheme for both vision and language transformers.
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations.
FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity
Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning.
Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation
Medical image segmentation is a fundamental task in the community of medical image analysis.
FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoring
To overcome this, we propose federated classifier anchoring (FCA) by adding a personalized classifier at each client to guide and debias the federated model through consistency learning.
Compete to Win: Enhancing Pseudo Labels for Barely-supervised Medical Image Segmentation
This study investigates barely-supervised medical image segmentation where only few labeled data, i. e., single-digit cases are available.
Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions
Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020.
Few Shot Medical Image Segmentation with Cross Attention Transformer
Our proposed network mines the correlations between the support image and query image, limiting them to focus only on useful foreground information and boosting the representation capacity of both the support prototype and query features.
Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation
Recently, the advent of vision Transformer (ViT) has brought substantial advancements in 3D dataset benchmarks, particularly in 3D volumetric medical image segmentation (Vol-MedSeg).
Exploring Visual Prompts for Whole Slide Image Classification with Multiple Instance Learning
Multiple instance learning (MIL) has emerged as a popular method for classifying histopathology whole slide images (WSIs).
Vessel-Promoted OCT to OCTA Image Translation by Heuristic Contextual Constraints
Our TransPro method is primarily driven by two novel ideas that have been overlooked by prior work.
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched.
Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networks
In this work, we propose a novel approach to semi-supervised regression, namely Uncertainty-Consistent Variational Model Ensembling (UCVME), which improves training by generating high-quality pseudo-labels and uncertainty estimates for heteroscedastic regression.
Oscillation-free Quantization for Low-bit Vision Transformers
In addition, we also found that the interdependence between quantized weights in $\textit{query}$ and $\textit{key}$ of a self-attention layer makes ViT vulnerable to oscillation.
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part.
Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos
We also introduce teacher-student distillation to distill the information from LV segmentation masks into an end-to-end LVEF regression model that only requires video inputs.
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples deviating from the normal profile as anomalies in the testing phase.
Graph Reasoning Transformer for Image Parsing
In this paper, we propose a novel Graph Reasoning Transformer (GReaT) for image parsing to enable image patches to interact following a relation reasoning pattern.
Dynamic Sub-Cluster-Aware Network for Few-Shot Skin Disease Classification
To achieve the objective of the second branch, we present a cluster loss to learn image similarities via unsupervised clustering.
InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation
Nuclei Segmentation from histology images is a fundamental task in digital pathology analysis.
BATFormer: Towards Boundary-Aware Lightweight Transformer for Efficient Medical Image Segmentation
Specifically, to fully explore the benefits of transformers in long-range dependency establishment, a cross-scale global transformer (CGT) module is introduced to jointly utilize multiple small-scale feature maps for richer global features with lower computational complexity.
The Lighter The Better: Rethinking Transformers in Medical Image Segmentation Through Adaptive Pruning
To our best knowledge, this is the first work on transformer pruning for medical image analysis tasks.
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification
In this paper, we present a privacy-preserving FL method named FedIIC to combat class imbalance from two perspectives: feature learning and classifier learning.
SDQ: Stochastic Differentiable Quantization with Mixed Precision
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used.
Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays
Subsequently, inter-discrepancy between the two modules, and intra-discrepancy inside the module that is trained on only normal images are designed as anomaly scores to indicate anomalies.
FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels.
Stereo Neural Vernier Caliper
We propose a new object-centric framework for learning-based stereo 3D object detection.
Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training
Third, a self-supervised visual representation learning method is tailored for nuclei segmentation of pathology images that transforms the hematoxylin component images into the H&E stained images to gain better understanding of the relationship between the nuclei and cytoplasm.
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework.
Data-Free Neural Architecture Search via Recursive Label Calibration
We identify that the NAS task requires the synthesized data (we target at image domain here) with enough semantics, diversity, and a minimal domain gap from the natural images.
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i. e., uniform strategy, due to its superior representational capacity.
Joint stereo 3D object detection and implicit surface reconstruction
We present a new learning-based framework S-3D-RCNN that can recover accurate object orientation in SO(3) and simultaneously predict implicit rigid shapes from stereo RGB images.
Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation
A stage-adaptive contrastive learning method is proposed, containing a boundary-aware contrastive loss that takes advantage of the labeled images in the first stage, as well as a prototype-aware contrastive loss to optimize both labeled and pseudo labeled images in the second stage.
Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network
We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.
R2F: A Remote Retraining Framework for AIoT Processors with Computing Errors
It takes the remote AIoT processor with soft errors in the training loop such that the on-site computing errors can be learned with the application data on the server and the retrained models can be resilient to the soft errors.
How Do Adam and Training Strategies Help BNNs Optimization?
We show the regularization effect of second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs.
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction
To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network.
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
This work aims to empirically clarify a recently discovered perspective that label smoothing is incompatible with knowledge distillation.
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
In this paper, we focus on this more difficult scenario: learning networks where both weights and activations are binary, meanwhile, without any human annotated labels.
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning
A common practice for this task is to train a model on the base set first and then transfer to novel classes through fine-tuning (Here fine-tuning procedure is defined as transferring knowledge from base to novel data, i. e. learning to transfer in few-shot scenario.)
Exploring intermediate representation for monocular vehicle pose estimation
The latter question motivates us to incorporate geometry knowledge with a new loss function based on a projective invariant.
Ranked #1 on
Vehicle Pose Estimation
on KITTI Cars Hard
Cascaded deep monocular 3D human pose estimation with evolutionary training data
End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data.
Ranked #13 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Joint Multi-Dimension Pruning via Numerical Gradient Update
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
Binarizing MobileNet via Evolution-based Searching
Inspired by one-shot architecture search frameworks, we manipulate the idea of group convolution to design efficient 1-Bit Convolutional Neural Networks (CNNs), assuming an approximately optimal trade-off between computational cost and model accuracy.
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
In this paper, we propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost.
Facial age estimation by deep residual decision making
Residual representation learning simplifies the optimization problem of learning complex functions and has been widely used by traditional convolutional neural networks.
Ranked #12 on
Age Estimation
on CACD
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
Together, the redefinition of latent weights as inertia and the introduction of Bop enable a better understanding of BNN optimization and open up the way for further improvements in training methodologies for BNNs.
Visualizing the decision-making process in deep neural decision forest
Deep neural decision forest (NDF) achieved remarkable performance on various vision tasks via combining decision tree and deep representation learning.
Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
Experimental results show that our method can effectively synthesize a large variety of mpMRI images which contain meaningful CS PCa lesions, display a good visual quality and have the correct paired relationship.
Synthesizing Multi-Parameter Magnetic Resonance Imaging (Mp-Mri) Data
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware gradient for weight updating, a better initialization method, and a two-step scheme for training a deep network.
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary.
