Search Results for author:
Found 61 papers, 34 papers with code
Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration
Opportunistic computed tomography (CT) analysis has emerged as a promising alternative for osteoporosis diagnosis using existing imaging data.
Airalogy: AI-empowered universal data digitization for research automation
In this study, we address these challenges by developing Airalogy (https://airalogy. com), the world's first AI- and community-driven platform that balances universality and standardization for digitizing research data across multiple disciplines.
Improving large language models with concept-aware fine-tuning
Large language models (LLMs) have become the cornerstone of modern AI.
Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query, consisting of a reference image and a modifying text-without relying on annotated training data.
R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length.
R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
To this end, we propose Share-GRPO, a novel RL approach that tackle these issues by exploring and sharing diverse reasoning trajectories over expanded question space.
Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation
Marine Saliency Segmentation (MSS) plays a pivotal role in various vision-based marine exploration tasks.
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Text-guided image editing is an essential task that enables users to modify images through natural language descriptions.
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
Recent studies generally enhance MLLMs' reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful reasoning paths without understanding what the wrong reasoning paths are.
Strategic priorities for transformative progress in advancing biology with proteomics and artificial intelligence
Artificial intelligence (AI) is transforming scientific research, including proteomics.
Reasoning with Reinforced Functional Token Tuning
Specifically, RFTT comprises two phases: (1) supervised fine-tuning performs prompt-driven tree search to obtain self-generated training data annotated with functional tokens, which warms up the model to learn these tokens for reasoning; and (2) online reinforcement learning further allows the model to explore different reasoning pathways through functional token sampling without relying on prompts, thereby facilitating effective self-improvement for functional reasoning.
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
These findings position PhysReason as a novel and comprehensive benchmark for evaluating physics-based reasoning capabilities in large language models.
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Mainstream defenses aim to vaccinate the model such that the later harmful fine-tuning attack is less effective.
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question.
SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing
While open-source video generation and editing models have made significant progress, individual models are typically limited to specific tasks, failing to meet the diverse needs of users.
A Survey on Vision Autoregressive Model
Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability.
Open-Vocabulary Object Detection via Language Hierarchy
LHST expands the image-level labels with language hierarchy and enables co-regularization between the expanded labels and self-training.
Historical Test-time Prompt Tuning for Vision Foundation Models
Test-time prompt tuning, which learns prompts online with unlabelled test samples during the inference stage, has demonstrated great potential by learning effective prompts on-the-fly without requiring any task-specific annotations.
Foundation Models for Remote Sensing and Earth Observation: A Survey
This survey systematically reviews the emerging field of RSFMs.
LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models
Several benchmarks have been created to gauge the hallucination levels of MLLMs, by either raising discriminative questions about the existence of objects or introducing LLM evaluators to score the generated text from MLLMs.
A Survey on Evaluation of Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) mimic human perception and reasoning system by integrating powerful Large Language Models (LLMs) with various modality encoders (e. g., vision, audio), positioning LLMs as the "brain" and various modality encoders as sensory organs.
Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures
A fundamental property of such structures is their topological self-similarity, which can be quantified by fractal features such as fractal dimension (FD).
Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model using 3D Whole-body CT Scans
Therefore, we propose two key technical developments: 1) a progressively and spatially aligned prompt encoding method to effectively encode click prompts in local 3D space; and 2) a cross-patch prompt scheme to capture more 3D spatial context, which is beneficial for reducing the editing workloads when interactively prompting on large organs.
Masked AutoDecoder is Effective Multi-Task Vision Generalist
Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction.
LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors
This paper presents DVDet, a Descriptor-Enhanced Open Vocabulary Detector that introduces conditional context prompts and hierarchical textual descriptors that enable precise region-text alignment as well as open-vocabulary detection training in general.
Domain Adaptation for Large-Vocabulary Object Detectors
Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data.
DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space.
Learning to Prompt Segment Anything Models
SAMs work with two types of prompts including spatial prompts (e. g., points) and semantic prompts (e. g., texts), which work together to prompt SAMs to segment anything on downstream datasets.
Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey
Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions.
Domain Generalization via Balancing Training Difficulty and Model Capability
Despite its recent progress, most existing work suffers from the misalignment between the difficulty level of training samples and the capability of contemporarily trained models, leading to over-fitting or under-fitting in the trained generalization model.
Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory
However, the source predictions of target data are often noisy and training with them is prone to learning collapses.
Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling target domains with different vocabularies.
Vision-Language Models for Vision Tasks: A Survey
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition paradigm.
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively.
XNet: Wavelet-Based Low and High Frequency Fusion Networks for Fully- and Semi-Supervised Semantic Segmentation of Biomedical Images
Perturbations in consistency-based semi-supervised models are often artificially designed.
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis.
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection.
Contextual Text Block Detection towards Scene Text Understanding
We formulate the new setup by a dual detection task which first detects integral text units and then groups them into a CTB.
Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
Specifically, we design cross-frame pseudo labelling to provide pseudo supervision from previous video frames while learning from the augmented current video frames.
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
Domain adaptive panoptic segmentation aims to mitigate data annotation challenge by leveraging off-the-shelf annotated data in one or multiple related source domains.
Ranked #3 on
Domain Adaptation
on Panoptic SYNTHIA-to-Cityscapes
Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
We build the balanced subclass distributions by clustering pixels of each original class into multiple subclasses of similar sizes, which provide class-balanced pseudo supervision to regularize the class-biased segmentation.
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA.
GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data
Specifically, we design GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training.
Contextual Text Detection
This paper presents Contextual Text Detection, a new setup that detects contextual text blocks for better understanding of texts in scenes.
Domain Adaptive Video Segmentation via Temporal Consistency Regularization
This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos.
Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
Extensive experiments show that SynLiDAR provides a high-quality data source for studying 3D transfer and the proposed PCT achieves superior point cloud translation consistently across the three setups.
FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition
Generative Adversarial Networks (GANs) have become the de-facto standard in image synthesis.
Spectral Unsupervised Domain Adaptation for Visual Recognition
Second, it introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample.
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation.
Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
We position the few labeled target samples as references that gauge the similarity between source and target features and guide adaptive inter-domain alignment for learning more similar source features.
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.
I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
The first task focuses on image-to-character (I2C) mapping which detects a set of character candidates from images based on different alignments of visual features in an non-sequential way.
DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
DA-DETR introduces a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains.
MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation.
FSDR: Frequency Space Domain Randomization for Domain Generalization
It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features.
Cross-View Regularization for Domain Adaptive Panoptic Segmentation
The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains.
Ranked #3 on
Domain Adaptation
on Panoptic SYNTHIA-to-Mapillary
FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively.
Ranked #25 on
3D Semantic Segmentation
on SemanticKITTI
Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively.
Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations.
Hierarchy Composition GAN for High-fidelity Image Synthesis
Despite the rapid progress of generative adversarial networks (GANs) in image synthesis in recent years, the existing image synthesis approaches work in either geometry domain or appearance domain alone which often introduces various synthesis artifacts.
