24 citations · 44 across the 35 of their papers we have counts for
38 papers
Shallow to Deep: Aligning Token Pruning with Stage-wise Roles in LVLMs
Shuo Zhang, Jintao Tong, Yixiong Zou +2
Large Vision-Language Models (LVLMs) incur high computational costs from redundant visual tokens. Although training-free attention-based multi-layer pruning in the vision encoder s…
Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection
Zijian Zhuang, Yixiong Zou, Yuhua Li +1
Cross-Domain Few-Shot Object Detection (CDFSOD) aims to transfer knowledge from data-rich upstream generic domains to downstream expert domains using scarce training data, where th…
Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation
Yuhan Liu, Yixiong Zou, Yuhua Li +1
Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries. While recent advances in Multimodal Large Language…
Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning
Haichen Zhou, Yazhe Lyu, Yixiong Zou +2
Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes with only a few samples while avoiding forgetting base classes. However, current methods show…
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
Shuai Yi, Yixiong Zou, Yuhua Li +1
Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-do…
Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
Shuai Yi, Yixiong Zou, Yuhua Li +1
Vision-language models (VLMs) like CLIP have shown impressive generalization capabilities, yet their potential for Cross-Domain Few-Shot Learning (CDFSL) remains underexplored, whe…
Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
Yaze Zhao, Yicong Liu, Yixiong Zou +2
Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot fine-tuning of vision-langua…
Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
Yaze Zhao, Yixiong Zou, Yuhua Li +1
Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the re…
Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
Yongwei Jiang, Yixiong Zou, Yuhua Li +1
Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain sh…
Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
Zhenyu Zhang, Yixiong Zou, Yuhua Li +2
Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Langua…
Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning
Zhenyu Zhang, Guangyao Chen, Yixiong Zou +2
Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where CLIP has rece…
SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
Jintao Tong, Shilin Yan, Hongwei Xue +5
Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform…
QKVQA: Question-Focused Filtering for Knowledge-based VQA
Wei Ye, Yixin Su, Yueguo Chen +4
Visual Question Answering (VQA) is the task of answering questions based on image content. Building upon this, Knowledge-Based VQA (KB-VQA) requires models to answer questions that…
Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
Jintao Tong, Jiaqi Gu, Yujing Lou +5
While Multimodal Large Language Models (MLLMs) excel at visual understanding tasks through text reasoning, they often fall short in scenarios requiring visual imagination. Unlike c…
Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
Shiwei Li, Xiandi Luo, Haozhao Wang +6
Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). LoRA essentially describes the projection of an input spa…
Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
Yang Qiu, Yixiong Zou, Jun Wang +3
Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimizat…
Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning
Yongwei Jiang, Yixiong Zou, Yuhua Li +1
Few-Shot Class-Incremental Learning (FSCIL) faces dual challenges of data scarcity and incremental learning in real-world scenarios. While pool-based prompting methods have demonst…
Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
Jintao Tong, Ran Ma, Yixiong Zou +3
Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain data…
Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
Shuai Yi, Yixiong Zou, Yuhua Li +1
Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant…
Random Registers for Cross-Domain Few-Shot Learning
Shuai Yi, Yixiong Zou, Yuhua Li +1
Cross-domain few-shot learning (CDFSL) aims to transfer knowledge from a data-sufficient source domain to data-scarce target domains. Although Vision Transformer (ViT) has shown su…
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
Jintao Tong, Yixiong Zou, Guangyao Chen +2
Cross-Domain Few-Shot Segmentation (CD-FSS) aims to transfer knowledge from a source-domain dataset to unseen target-domain datasets with limited annotations. Current methods typic…
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
Shiwei Li, Xiandi Luo, Xing Tang +6
Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method. In standard LoRA layers, one of the matrices, or , is initialized to zero, ensuring that…
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
Shiwei Li, Xiandi Luo, Haozhao Wang +6
To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we…
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
Jintao Tong, Wenwei Jin, Pengda Qin +5
Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically r…