Search Results for author:
Found 48 papers, 21 papers with code
Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability
By viewing ResNet as an explicit Euler discretization of an ordinary differential equation (ODE), for the first time, we find that the adversarial robustness of ResNet is connected to the numerical stability of the corresponding dynamic system.
Towards Interpretable Counterfactual Generation via Multimodal Autoregression
We further introduce ProgEmu, an autoregressive model that unifies the generation of counterfactual images and textual interpretations.
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e. g., LoRA) will become essential due to their efficiency in reducing computation costs.
HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation
Specifically, our approach extracts both time-shared and time-specific features from longitudinal chest X-rays and diagnostic reports to capture disease progression.
MADE: Graph Backdoor Defense with Masked Unlearning
Graph Neural Networks (GNNs) have garnered significant attention from researchers due to their outstanding performance in handling graph-related tasks, such as social network analysis, protein design, and so on.
Artificial Intelligence-Enhanced Couinaud Segmentation for Precision Liver Cancer Therapy
Precision therapy for liver cancer necessitates accurately delineating liver sub-regions to protect healthy tissue while targeting tumors, which is essential for reducing recurrence and improving survival rates.
On the Adversarial Transferability of Generalized "Skip Connections"
Specifically, in ResNet-like models (with skip connections), we find that using more gradients from the skip connections rather than the residual modules according to a decay factor during backpropagation allows one to craft adversarial examples with high transferability.
SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal
Adverse weather removal aims to restore clear vision under adverse weather conditions.
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
This convergence introduces similar privacy risks for generated data to those associated with real data.
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
Additionally, with the reversed trigger, we propose backdoor detection from the noise space, introducing the first backdoor input detection approach for diffusion models and a novel model detection algorithm that calculates the KL divergence between reversed and benign distributions.
Medical Report Generation Is A Multi-label Classification Problem
However, in this paper, we propose a novel perspective: rethinking medical report generation as a multi-label classification problem.
Image Super-Resolution with Taylor Expansion Approximation and Large Field Reception
This softmax makes the matrix multiplication between Query and Key inseparable, posing a great challenge in simplifying computational complexity.
Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
By leveraging this concept, CoFE can learn non-spurious visual representations by contrasting the representations between factual and counterfactual images.
CLIPVQA:Video Quality Assessment via CLIP
To utilize the quality language descriptions of videos for supervision, we develop a CLIP-based encoder for language embedding, which is then fully aggregated with the generated content information via a cross-attention module for producing video-language representation.
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
Drawing on these insights, we propose a simple yet effective method called \textbf{Prompt-Independent Defense (PID)} to safeguard privacy against LDMs.
Teaching with Uncertainty: Unleashing the Potential of Knowledge Distillation in Object Detection
In this paper, we propose a novel feature-based distillation paradigm with knowledge uncertainty for object detection, termed "Uncertainty Estimation-Discriminative Knowledge Extraction-Knowledge Transfer (UET)", which can seamlessly integrate with existing distillation methods.
Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification
(b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations.
Black-box Adversarial Attacks Against Image Quality Assessment Models
Specifically, we first formulate the attack problem as maximizing the deviation between the estimated quality scores of original and perturbed images, while restricting the perturbed image distortions for visual quality preservation.
EMBRE: Entity-aware Masking for Biomedical Relation Extraction
Information extraction techniques, including named entity recognition (NER) and relation extraction (RE), are crucial in many domains to support making sense of vast amounts of unstructured text data by identifying and connecting relevant information.
Mask Propagation for Efficient Video Semantic Segmentation
By reusing predictions from key frames, we circumvent the need to process a large volume of video frames individually with resource-intensive segmentors, alleviating temporal redundancy and significantly reducing computational costs.
Explaining How a Neural Network Play the Go Game and Let People Learn
The AI model has surpassed human players in the game of Go, and it is widely believed that the AI model has encoded new knowledge about the Go game beyond human players.
Data navigation on the ENCODE portal
Spanning two decades, the Encyclopaedia of DNA Elements (ENCODE) is a collaborative research project that aims to identify all the functional elements in the human and mouse genomes.
Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
For faithfulness, we prove the uniqueness of the AND (OR) interaction in quantifying the effect of the AND (OR) relationship between input variables.
A Benchmark for Cycling Close Pass Near Miss Event Detection from Video Streams
Instance-level detection aims to detect which vehicle in the scene gives rise to a close pass near miss.
Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?
In this paper, we explain the inference logic of large language models (LLMs) as a set of symbolic concepts.
Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation
To address the limitation, we propose a knowledge graph with Dynamic structure and nodes to facilitate medical report generation with Contrastive Learning, named DCL.
Does a Neural Network Really Encode Symbolic Concepts?
Recently, a series of studies have tried to extract interactions between input variables modeled by a DNN and define such interactions as concepts encoded by the DNN.
Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System
This curriculum-driven noise introduction aids the memory-driven decoder by supplying more diverse and representative training data, enhancing the decoder's ability to model seasonal tendencies and dependencies in the time-series data.
Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition
Fault diagnosis is critical in many domains, as faults may lead to safety threats or economic losses.
Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation
To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure.
SymNMF-Net for The Symmetric NMF Problem
Furthermore, we analyze the constraints of the inversion layer to ensure the output stability of the network to a certain extent.
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs
Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN's complexity.
Defining and Quantifying the Emergence of Sparse Concepts in DNNs
This paper aims to illustrate the concept-emerging phenomenon in a trained DNN.
Visualizing the Emergence of Intermediate Visual Patterns in DNNs
This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN.
Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
In this paper, we endeavor to design strategies to achieve universal adversarial robustness.
Generating Watermarked Adversarial Texts
Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models.
Optimization inspired Multi-Branch Equilibrium Models
Works have shown the strong connections between some implicit models and optimization problems.
FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark
Researchers have explored advanced methods from computer vision and natural language processing to incorporate medical domain knowledge for the generation of readable medical reports.
Disentanglement, Visualization and Analysis of Complex Features in DNNs
This paper aims to define, visualize, and analyze the feature complexity that is learned by a DNN.
Towards Understanding and Improving Dropout in Game Theory
Experimental results on various DNNs and datasets have shown that the interaction loss can effectively improve the utility of dropout and boost the performance of DNNs.
Understanding, Analyzing, and Optimizing the Complexity of Deep Models
Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN’s complexity.
Interpreting and Boosting Dropout from a Game-Theoretic View
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions.
Interpreting and Disentangling Feature Components of Various Complexity from DNNs
This paper aims to define, quantify, and analyze the feature complexity that is learned by a DNN.
Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
Firstly, the regions of primary interest to radiologists are usually located in a small area of the global image, meaning that the remainder parts of the image could be considered as irrelevant noise in the training procedure.
An Action Recognition network for specific target based on rMC and RPN
Meanwhile, the action recognition network is tested in our gesture and body posture data sets for specific target.
Impoved RPN for Single Targets Detection based on the Anchor Mask Net
Common target detection is usually based on single frame images, which is vulnerable to affected by the similar targets in the image and not applicable to video images.
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
In this paper, we are interested in building lightweight and efficient convolutional neural networks.
