Search Results for author:
Found 57 papers, 31 papers with code
Knowledge Swapping via Learning and Unlearning
We introduce \textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\-specified information, retaining essential knowledge, and acquiring new knowledge simultaneously.
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
Building on this insight, we propose a novel semantic drift calibration method that incorporates mean shift compensation and covariance calibration.
Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
This paper presents the HFUT-LMC team's solution to the WWW 2025 challenge on Text-based Person Anomaly Search (TPAS).
ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4). Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for accurately manipulation detection and grounding.
Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation
To address this, we propose a novel framework, Sign-D2C, that employs a conditional diffusion model to synthesize contextually smooth transition frames, enabling the seamless construction of continuous sign language sequences.
Modality Alignment Meets Federated Broadcasting
Federated learning (FL) has emerged as a powerful approach to safeguard data privacy by training models across distributed edge devices without centralizing local data.
FoPru: Focal Pruning for Efficient Large Vision-Language Models
Large Vision-Language Models (LVLMs) represent a significant advancement toward achieving superior multimodal capabilities by enabling powerful Large Language Models (LLMs) to understand visual input.
Dataset Distillers Are Good Label Denoisers In the Wild
Learning from noisy data has become essential for adapting deep learning models to real-world applications.
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
The innovation of our approach is that we leverage the diffusion model's intrinsic data reconstruction ability to distinguish ID samples from OOD samples in the latent feature space.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning
Recent advancements in image-text matching have been notable, yet prevailing models predominantly cater to broad queries and struggle with accommodating fine-grained query intention.
Benchmarking Multi-Scene Fire and Smoke Detection
The current irregularities in existing public Fire and Smoke Detection (FSD) datasets have become a bottleneck in the advancement of FSD technology.
Fire and Smoke Detection with Burning Intensity Representation
To address this issue, a new Attentive Fire and Smoke Detection Model (a-FSDM) is proposed.
Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing
Text-driven video editing utilizing generative diffusion models has garnered significant attention due to their potential applications.
MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection
Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies.
A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
Consequently, various face forgery detection techniques have been proposed to identify such fake facial content.
FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation
Specifically, we employ a local prompt tuning scheme that leverages a few learnable visual prompts to efficiently fine-tune the frozen pre-trained foundation model for downstream tasks, thereby accelerating training and improving model performance under limited local resources and data heterogeneity.
Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models' performance can be significantly improved when pre-trained with our method.
ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Prediction
Metro Origin-Destination (OD) prediction is a crucial yet challenging spatial-temporal prediction task in urban computing, which aims to accurately forecast cross-station ridership for optimizing metro scheduling and enhancing overall transport efficiency.
LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Field
In this paper, inspired by significant progress in the field of novel view synthesis (NVS) achieved by 3D Gaussian Splatting (3D-GS), we propose LoopGaussian to elevate cinemagraph from 2D image space to 3D space using 3D Gaussian modeling.
KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques
In this work, we develop an augmented LLM framework, KG-Rank, which leverages a medical knowledge graph (KG) along with ranking and re-ranking techniques, to improve the factuality of long-form question answering (QA) in the medical domain.
Revisiting the Power of Prompt for Visual Tuning
Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes.
Ranked #1 on
Visual Prompt Tuning
on VTAB-1k(Structured<8>)
Open-Vocabulary Video Relation Extraction
A comprehensive understanding of videos is inseparable from describing the action with its contextual action-object interactions.
Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation
Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field.
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular.
Integrating UMLS Knowledge into Large Language Models for Medical Question Answering
Our research demonstrates the effectiveness of using UMLS-augmented LLMs and highlights the potential application value of LLMs in in medical question-answering.
NLPBench: Evaluating Large Language Models on Solving NLP Problems
Recent developments in large language models (LLMs) have shown promise in enhancing the capabilities of natural language processing (NLP).
ScrollTimes: Tracing the Provenance of Paintings as a Window into History
The study of cultural artifact provenance, tracing ownership and preservation, holds significant importance in archaeology and art history.
Improving Knowledge Distillation via Regularizing Feature Norm and Direction
Finally, we propose a rather simple loss term (dubbed ND loss) to simultaneously (1) encourage student to produce large-\emph{norm} features, and (2) align the \emph{direction} of student features and teacher class-means.
Ranked #1 on
Knowledge Distillation
on COCO 2017 val
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation.
Contrastive Learning
Weakly supervised Semantic Segmentation
+1
Mitigating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
A surge of interest has emerged in weakly supervised semantic segmentation due to its remarkable efficiency in recent years.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Life Regression based Patch Slimming for Vision Transformers
In this study, we tackle the patch slimming problem from a different perspective by proposing a life regression module that determines the lifespan of each image patch in one go.
ViT-Calibrator: Decision Stream Calibration for Vision Transformer
In this work, we propose a new paradigm dubbed Decision Stream Calibration that boosts the performance of general Vision Transformers.
Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning
This is specifically achieved by devising an elaborated ``prophetic'' teacher, termed as ``Propheter'', that aims to learn the potential class distributions.
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.
Model Doctor for Diagnosing and Treating Segmentation Error
Despite the remarkable progress in semantic segmentation tasks with the advancement of deep neural networks, existing U-shaped hierarchical typical segmentation networks still suffer from local misclassification of categories and inaccurate target boundaries.
Team DETR: Guide Queries as a Professional Team in Detection Transformers
Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance.
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics
We set up novel evaluation benchmarks based on a series of testing sets with evolving distributions.
Ranked #66 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt
Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels.
Text-Guided Mask-free Local Image Retouching
In the realm of multi-modality, text-guided image retouching techniques emerged with the advent of deep learning.
SASFormer: Transformers for Sparsely Annotated Semantic Segmentation
In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance.
Compound Batch Normalization for Long-tailed Image Classification
It can model the feature space more comprehensively and reduce the dominance of head classes.
Transferability Estimation Based On Principal Gradient Expectation
Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks.
A Survey of Neural Trees
This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability.
Combating Noisy Labels in Long-Tailed Image Classification
Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions.
ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background.
Dual Domain-Adversarial Learning for Audio-Visual Saliency Prediction
The domain discrepancy induces to performance degradation on target testing data for CNN models.
Re-Attention Transformer for Weakly Supervised Object Localization
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories.
Long-term Leap Attention, Short-term Periodic Shift for Video Classification
By replacing a vanilla 2D attention with the LAPS, we could adapt a static transformer into a video one, with zero extra parameters and neglectable computation overhead ($\sim$2. 6\%).
KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing
In this article, we propose a Knowledge Embedded RCNN (KE-RCNN) to identify attributes by leveraging rich knowledges, including implicit knowledge (e. g., the attribute ``above-the-hip'' for a shirt requires visual/geometry relations of shirt-hip) and explicit knowledge (e. g., the part of ``shorts'' cannot have the attribute of ``hoodie'' or ``lining'').
Cross-Modality High-Frequency Transformer for MR Image Super-Resolution
Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.
Knowledge Distillation
Weakly supervised Semantic Segmentation
+1
Visual Boundary Knowledge Translation for Foreground Segmentation
To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators.
Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming.
Boundary Knowledge Translation based Reference Semantic Segmentation
In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation.
Intrinsic Image Transformation via Scale Space Decomposition
We introduce a new network structure for decomposing an image into its intrinsic albedo and shading.
