← Back to all news
arXiv Computer Vision

Open-Vocabulary Models and Label Propagation for Uncertainty-aware Pseudo-Labeling of Object Detection Datasets

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.

Related stories

arXiv Computer Vision
Sep 21

Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty

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
computer-visionbenchmarksdata-engineering
More like this →
arXiv Computer Vision
Sep 7

Object Concepts Emerge from Motion

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
computer-vision
More like this →
Hugging Face Trending Papers
Sep 3

Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language

The paper introduces set difference captioning for autonomous driving datasets, aiming to generate natural‑language descriptions of differences between two image subsets. It adapts a two‑stage approach to focus on object‑centric patches, enabling attribution of differences to specific objects or categories. A new benchmark, AD‑Diff Bench, is presented to evaluate this method, especially for sparse, real‑world differences, and the authors provide open‑weight models and code for reproducibility.

agentscomputer-visionroboticsbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 4

Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language

The paper introduces set difference captioning for autonomous driving datasets, aiming to generate natural‑language descriptions of differences between two image subsets. It adapts a two‑stage approach to focus on object‑centric patches, allowing attribution of differences to specific objects or categories. A new benchmark, AD‑Diff Bench, is presented to evaluate these methods, especially for sparse, real‑world differences, with open‑weight models to ensure reproducibility.

By Julian Truetsch, Felix Hauser, Christoph Stiller, Frank Bieder
agentscomputer-visionroboticsbenchmarkssafety
More like this →
arXiv AI
Sep 1

Background-Free Objectness Learning for Class-Agnostic Detection

Background-Free Objectness Learning (B-FOR) is a dense, class‑agnostic detection framework that learns objectness without treating unlabeled regions as background. It predicts multi‑scale object‑center and scale fields, using spatially structured soft targets to supervise only reliable annotated areas and introduces displacement‑aware scale fields to model object extent. Experiments on PASCAL VOC, MS‑COCO, and Open Images show B‑FOR improves recall by over +10 AR points compared to prior class‑agnostic baselines, with ablation studies confirming the importance of localized supervision and displacement‑aware scaling.

By Dania Batool, Liliana Lo Presti, Marco La Cascia, Filippo Vella
benchmarkssafety
More like this →