The paper demonstrates that object detection benchmarks suffer from incomplete annotations, with re-annotation of COCO, Pascal VOC, Cityscapes, and KITTI revealing up to a 60% increase in detected objects, especially small, occluded, or densely packed instances. The authors propose a scalable annotation pipeline that uses multiple annotators per object to capture uncertainty and improve recall, and they introduce two new large-scale benchmarks: an uncertainty-aware detection benchmark and a label error detection benchmark based on real errors. Their findings show that benchmark performance is highly sensitive to annotation quality, yet model rankings remain largely unchanged, highlighting the need for uncertainty-aware evaluation to better reflect real-world ambiguity.
By Sarina Penquitt, Jonathan Klees, Antonia van Betteray, Parssa Jashnieh, Peter Stehr, Matthias Rottmann, Lars Schmarje
The paper presents a semi‑supervised framework that uses open‑vocabulary object detectors to generate region proposals and semantic representations, builds an object‑level similarity graph, and propagates probabilistic labels to assign soft, uncertainty‑aware annotations to previously unlabeled objects. Experiments on four detection benchmarks show that high‑quality soft labels can be produced with only a small fraction of manual annotations, and models trained on these semi‑automatically annotated datasets achieve performance comparable to fully manually annotated models. On COCO, the method reaches 40.5% AP, nearly matching the 40.9% AP of a fully annotated model while incurring only 1% of the labeling cost.
By Jonathan Klees, Timo Heller, Matthias Rottmann
arXiv:2605. 29539v2 Announce Type: replace-cross Abstract: Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD).
By Jiacong Liu, Shu Luo, Yikai Qin, Yaze Zhao, Yongwei Jiang, Yixiong Zou
OpenBox is a two‑stage automatic annotation pipeline that uses a 2D vision foundation model to associate 2D image cues with 3D point clouds. It then classifies instances by rigidity and motion state to generate adaptive bounding boxes using class‑specific size statistics, eliminating the need for self‑training. Experiments on Waymo Open Dataset, Lyft Level 5 Perception, and nuScenes show improved accuracy and efficiency over existing baselines.
By In-Jae Lee, Mungyeom Kim, Kwonyoung Ryu, Pierre Musacchio, Jaesik Park
arXiv:2608.29917v1 Announce Type: new
Abstract: Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes...
By Gabriele Trivigno, Marcos Alfaro, Claudia Cuttano, Gabriele Berton, Luis Pay\'a, Carlo Masone
WeVisOne‑VL is a new vision‑language model that unifies object‑level and pixel‑level perception through structured next‑token prediction. It supports a wide range of visual tasks—object detection, referring localization, counting, OCR, segmentation, and matting—allowing localization at any user‑specified granularity from points and boxes to masks and alpha mattes. The architecture incorporates a lightweight pixel decoder via a special token, and the model is trained with a three‑stage curriculum followed by mixed‑task reinforcement learning, achieving leading performance on over 30 benchmarks while robustly rejecting object‑absent queries.
By Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu
UnSAMv2 is a self‑supervised extension of the Segment Anything Model that can segment objects at any granularity without human annotations. It discovers mask‑granularity pairs and introduces a granularity control embedding for continuous scale adjustment, requiring only 6K unlabeled images and 0.02% extra parameters. The model outperforms SAM/SAM‑2 across 11+ benchmarks, improving metrics such as 1‑IoU from 58.0 to 73.1 and achieving state‑of‑the‑art performance on language‑guided segmentation.
By Junwei Yu, Trevor Darrell, XuDong Wang
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.
By Boshi Li, Xiaohui Wang, Xiaoyang Wu, Zhichao Li, Ya Yang, Naiyan Wang
Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes the object within a target image, the latter retr...
RGBD20K is a new large-scale RGB‑D semantic segmentation dataset featuring 20,000 image pairs and 160 fine‑grained categories, surpassing existing benchmarks like NYUv2 and SUN RGB‑D in both scale and semantic diversity. The dataset provides high‑fidelity annotations obtained through rigorous re‑evaluation and correction of prior labels, ensuring a clean ground‑truth foundation. Additionally, the authors introduce a score‑purified fusion (SPF) method that achieves state‑of‑the‑art performance across evaluated benchmarks, demonstrating the value of high‑quality multimodal information.
By Shaohua Dong, Zexuan Meng, Haiyan Sun, Bing Fan, Cuicui Zhang, Dylan Joseph, Kewei Sha, Yunhe Feng, Heng Fan
arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.
By Glenn Jocher, Jing Qiu, Mengyu Liu, Shuai Lyu, Fatih Cagatay Akyon, Muhammet Esat Kalfaoglu
SOCO is a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. It also includes keypoint language descriptions, enabling evaluation of large vision‑language models and their fine‑grained part‑level understanding. Experiments show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories, LVLMs excel at text‑prompted part localization but lag in visual‑reference matching, and correspondence performance predicts dense downstream tasks more strongly than ImageNet classification.
By Olaf D\"unkel, Basavaraj Sunagad, Haoran Wang, David T. Hoffmann, Christian Theobalt, Adam Kortylewski