Research Project: ENabling Self-Driving in Uncertain Real Environments
Loading...
Contributors
Funders
ID
EC.00190
Authors
Güney, Fatma
Faculty Member
Publications
O1O: Grouping of known classes to identify unknown objects as odd-one-out
(Springer, 2025) Güney, Fatma; Yavuz, Mısra; Department of Computer Engineering; KUIS AI (Koç University & İş Bank Artificial Intelligence Center); Yes; Yavuz, Mısra; College of Engineering
Object detection methods trained on a fixed set of known classes struggle to detect objects of unknown classes in the open-world setting. Current fixes involve adding approximate supervision with pseudo-labels corresponding to candidate locations of objects, typically obtained in a class-agnostic manner. While previous approaches mainly rely on the appearance of objects, we find that geometric cues improve unknown recall. Although additional supervision from pseudo-labels helps to detect unknown objects, it also introduces confusion for known classes. We observed a notable decline in the model’s performance for detecting known objects in the presence of noisy pseudo-labels. Drawing inspiration from studies on human cognition, we propose to group known classes into superclasses. By identifying similarities between classes within a superclass, we can identify unknown classes through an odd-one-out scoring mechanism. Our experiments on open-world detection benchmarks demonstrate significant improvements in unknown recall, consistently across all tasks. Crucially, we achieve this without compromising known performance, thanks to better partitioning of the feature space with superclasses. Project page: https://kuis-ai.github.io/O1O. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
A likelihood ratio-based approach to segmenting unknown objects
(Springer, 2025) Nayal, Nazir; Güney, Fatma; Shoeb, Youssef; Department of Computer Engineering; KUIS AI (Koç University & İş Bank Artificial Intelligence Center); Yes; College of Engineering; Research Center
Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD remains mostly unexplored. We seek to leverage a large foundational model to achieve robust representation. Outlier supervision is a widely used strategy for improving OoD detection of the existing segmentation networks. However, current approaches for outlier supervision involve retraining parts of the original network, which is typically disruptive to the model's learned feature representation. Furthermore, retraining becomes infeasible in the case of large foundational models. Our goal is to retrain for outlier segmentation without compromising the strong representation space of the foundational model. To this end, we propose an adaptive, lightweight unknown estimation module (UEM) for outlier supervision that significantly enhances the OoD segmentation performance without affecting the learned feature representation of the original network. UEM learns a distribution for outliers and a generic distribution for known classes. Using the learned distributions, we propose a likelihood-ratio-based outlier scoring function that fuses the confidence of UEM with that of the pixel-wise segmentation inlier network to detect unknown objects. We also propose an objective to optimize this score directly. Our approach achieves a new state-of-the-art across multiple datasets, outperforming the previous best method by 5.74% average precision points while having a lower false-positive rate. Importantly, strong inlier performance remains unaffected. The code and pre-trained models are available at: https://github.com/NazirNayal8/UEM-likelihood-ratio.
Segment-level road obstacle detection using visual foundation model priors and likelihood ratios
(Science and Technology Publications, Lda, 2025) Nayal, Nazir; Güney, Fatma; Nowzad, Azarm; Gottschalk, Hanno; Shoeb, Youssef; Department of Computer Engineering; Yes; College of Engineering
Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign a score to each pixel and apply a threshold to generate final predictions. However, selecting an appropriate threshold is challenging, and the per-pixel classification approach often leads to fragmented predictions with numerous false positives. In this work, we propose a novel method that leverages segment-level features from visual foundation models and likelihood ratios to predict road obstacles directly. By focusing on segments rather than individual pixels, our approach enhances detection accuracy, reduces false positives, and offers increased robustness to scene variability. We benchmark our approach against existing methods on the RoadObstacle and LostAndFound datasets, achieving state-of-the-art performance without needing a predefined threshold.
