10 accepted papers
Multimodal large language models (MLLMs) achieve remarkable progress in cross-modal perception and reasoning, yet a fundamental question remains unresolved: should the vision encoder be fine-tuned or frozen? Despite the success of models such as LLaVA and Qwen-VL, inconsistent design choices and het
Interactive segmentation aims to delineate a user-specified target in an image by leveraging positive and negative clicks. While effective on natural images, existing methods often fail in remote sensing scenarios, where satellite imagery is characterized by ultra-high resolution, sparse object dist
Global path planning provides high-level guidance for autonomous navigation, supplying reference paths for downstream navigation and control modules. Deep Reinforcement Learning (DRL) has shown strong potential in this domain, but existing methods struggle with multi-scale map inputs. This limitatio…
Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remarkable photorealistic image synthesis, their potential in complex visual segmentation tasks remains underexplored. In this…
Document image rectification aims to eliminate geometric deformation in photographed documents to facilitate text recognition. However, existing methods often neglect the significance of foreground elements, which provide essential geometric references and layout information for document image corre…
Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning paradigm. However, existing methods often struggle to accurat…
Parameter Efficient Transfer Learning (PETL) excels in downstream classification fine-tuning with minimal computational overhead, demonstrating its potential within the pre-train and fine-tune paradigm. However, recent PETL methods consistently struggle when fine-tuning for semantic segmentation tas…
"Object detection is an important task that finds its application in a wide range of scenarios. Generally, it requires extensive labels for training, which is quite time-consuming, especially in crowded scenes. Recently, Segment Anything Model (SAM) has emerged as a powerful zero-shot segmenter, off…
The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by initializing or regularizing the downstream model based on the pretr…
"Contrastive learning has shown great potential in video representation learning. However, existing approaches fail to sufficiently exploit short-term motion dynamics, which are crucial to various down-stream video understanding tasks. In this paper, we propose Motion Sensitive Contrastive Learning…