Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection
In this paper, we consider the imperfection within machine learning-based 2D object detection and its impact on safety. We address a special sub-type of performance limitations: the prediction bounding box cannot be perfectly aligned with the ground truth, but the computed Intersection-over-Union metric is always larger than a given threshold. Under such type of performance limitation, we formally prove the minimum required bounding box enlargement factor to cover the ground truth. We then demonstrate that the factor can be mathematically adjusted to a smaller value, provided that the motion planner takes a fixed-length buffer in making its decisions. Finally, observing the difference between an empirically measured enlargement factor and our formally derived worst-case enlargement factor offers an interesting connection between the quantitative evidence (demonstrated by statistics) and the qualitative evidence (demonstrated by worst-case analysis).
Code (0)
등록된 구현이 없습니다.
Tasks
2D Object Detectionobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human prefe…
Red TeamingCRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras
Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution ($346 \times 260$) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, an…
Object TrackingUnpredictability of AI
The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is im…
Decoupled Alignment for Robust Plug-and-Play Adaptation
We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to …
Knowledge DistillationImmersion and Invariance-based Disturbance Observer and Its Application to Safe Control
When the disturbance input matrix is nonlinear, existing disturbance observer design methods rely on the solvability of a partial differential equation or the existence of an output function with a uniformly well-defined…