CLSC DETR introduces a Cross Layer Local Support module that links final layer queries with intermediate layer candidates to gather complementary geometric evidence, improving localization quality estimation for small UAV objects. A Classification and Localization Consistency Calibration module then adjusts classification scores based on this quality and reliability, enhancing candidate ranking. The method yields a 1.5% AP and 2.0% AP$_{75}$ boost on VisDrone and consistent gains on UAVDT.
By Junyan Lin
arXiv:2511.05782v3 Announce Type: replace
Abstract: Unsupervised domain adaptation (UDA) for medical image segmentation remains challenging due to substantial domain shifts across imaging modalities,...
By Lalit Maurya, Honghai Liu, Reyer Zwiggelaar
The paper introduces Language-driven Dense Semantic Adaptor (LDSA) for multi-label image classification with incomplete annotations. LDSA leverages multimodal pretrained CLIP models to extract prior-adaptive relationships, employing a densely contrastive adaptor for visual contrastive constraints and a language-driven interactive decoder with class-specific prompt tuning. Experiments show LDSA achieves state‑of‑the‑art performance on public benchmarks and reveals implicit semantic relationships through its learning scheme.
By Cheng Chen, Yifan Zhao, Jia Li
The paper evaluates how well Vision Transformers (ViTs) can handle token merging techniques—specifically ToMe and Mutual Pair Merging—across wheat phenotyping tasks such as growth-stage classification, wheat-head detection, and wheat-organ segmentation. It benchmarks task quality, throughput, token count, and GPU memory usage, including tests on a Raspberry Pi 5. Results show that classification is highly tolerant to token merging, whereas detection and segmentation suffer due to factors like repeated instances, thin organs, dense boundaries, and runtime overhead, and that optimized attention backends can negate apparent speed gains.
By Simon Rav\'e, Pejman Rasti, David Rousseau
SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
By JeongRae Kim, Chaehyun Kim, Changwon Lim
arXiv:2608.22679v1 Announce Type: new
Abstract: Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as...
By Changki Sung, Hyungtae Lim, Wanhee Kim, Youngwoo Seo, Hyun Myung
arXiv:2501.16760v2 Announce Type: replace
Abstract: Automated interpretation of seismic images using deep learning methods is challenging because of the limited availability of training data. Few-sho...
By Surojit Saha, Ross Whitaker
arXiv:2608.22289v1 Announce Type: new
Abstract: Unmanned aerial vehicles (UAVs) increasingly require robust visual localization in GNSS-denied environments. A common solution estimates UAV poses by m...
By Yibin Ye, Xichao Teng, Shuo Chen, Xiaokai Song, Dongdong Guan, Qifeng Yu, Zhang Li
The paper introduces an Attention-Driven Complementarity Resampling framework to enhance cross-modality object detection. It employs a shared channel spatial attention mechanism that exchanges semantic masks between modalities, encouraging the backbone to learn generalized features. Additionally, a learnable channel competition module samples and aggregates features channel‑wise, improving robustness and achieving competitive results on multiple datasets.
By Guandi Wang, Ming Li, Yunsen Xing, Junle Liu
arXiv:2501.04001v4 Announce Type: replace
Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...
By Haobo Yuan, Xiangtai Li, Tao Zhang, Yueyi Sun, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang
The paper introduces SASC-USOD, a framework for underwater salient object detection that learns spatially adaptive coordination between two structural representations: a boundary-sensitive representation using Laplacian filtering and a region-coherent representation via dual-range anisotropic large-kernel aggregation. A spatial coordination module estimates the relative reliability of these representations and adaptively blends them based on image content. Experiments on USOD10K and USOD benchmarks show that SASC-USOD outperforms existing methods, reducing MAE by 4.07% and 23.53% respectively, and its lightweight variant achieves 21 FPS on an NVIDIA Jetson TX2 NX.
By Lin Hong, Chenhui Wang, Linan Deng, Yuning Cui, Yu Zhang, Xin Wang, Bojian Zhang, Xingchen Yang, Fumin Zhang
arXiv:2506.20756v4 Announce Type: replace
Abstract: Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pr...
By Haodong Li, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu
Segmenting ischemic stroke lesions on T1-weighted (T1w) MRI acquired across different scanners and protocols without intensity standardization is difficult because lesions are subtle and share intensi...
Lung cancer tissue diagnostics is complex, as therapy decisions in precision oncology rely on the integration of histomorphological, immunohistochemical, and molecular features. Yet pathological asses...
In light-field (LF) imaging systems, dense spatial sampling from a camera array enables powerful post-capture capabilities such as refocusing and depth estimation. However, real-world LF capture is of...
3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis. However, existing generative models typically synthesize 3D volumes monolith...
Referring Expression Segmentation (RES) aims to generate a pixel-level mask for the object specified by a language expression. Recent methods based on multimodal large language models (MLLMs) often re...
arXiv:2608.20868v1 Announce Type: cross
Abstract: Document processing pipelines traditionally cascade optical character recognition (OCR) engines with downstream models for structured information ext...
By A. Said Gurbuz (IBM Research Zurich, ETH Zurich), Ahmed Nassar (IBM Research Zurich), Christoph Auer (IBM Research Zurich), Maksym Lysak (IBM Research Zurich), Lucas Morin (IBM Research Zurich), Matteo Omenetti (IBM Research Zurich), Tim Strohmeyer (IBM Research Zurich), Panagiotis Vagenas (IBM Research Zurich), Nikolaos Livathinos (IBM Research Zurich), Michele Dolfi (IBM Research Zurich), Peter Staar (IBM Research Zurich)
arXiv:2608.21023v1 Announce Type: new
Abstract: Word alignment has traditionally been studied between sentences, but many cross-lingual tasks increasingly require correspondences across full document...
By Michelle Wastl, Jannis Vamvas, Rico Sennrich
arXiv:2608.21133v1 Announce Type: new
Abstract: Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barri...
By Shiva Shrestha, Zongxing Xie, Chen Zhao, Liran Ma, Zhipeng Cai, Honghui Xu