BDD100K
PulseAugur coverage of BDD100K — every cluster mentioning BDD100K across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New defense detects adversarial attacks on DNNs with 99.9% accuracy
Researchers have developed a novel method for detecting adversarial attacks on Deep Neural Networks (DNNs) used in autonomous driving systems. This approach leverages inconsistencies between multiple vision tasks, such …
-
Optimized RetinaNet Architecture Achieves Real-Time Semantic Segmentation for Automotive Systems
Researchers have developed an optimized semantic segmentation architecture called Opt-RetinaSeg, derived from the RetinaNet detection framework, specifically for real-time perception in embedded automotive systems. This…
-
New framework OKR enhances domain-incremental object detection
Researchers have introduced Orthogonal Knowledge Refreshing (OKR), a novel framework designed to improve domain-incremental object detection (DIOD). OKR addresses the challenge of models adapting to new data domains wit…
-
New framework COVTrack++ advances open-vocabulary multi-object tracking
Researchers have introduced COVTrack++, a novel framework designed to enhance open-vocabulary multi-object tracking (OVMOT) in continuous videos. The system addresses limitations in current OVMOT by constructing C-TAO, …
-
New study "Robust Onion" analyzes noise impact on object detectors
A new study titled "Robust Onion" investigates the impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs). The research uses controlled synthetic degradations to analyze how and why these detectors lose…
-
UniDrive framework unifies vision-language and grounding for autonomous driving risk understanding · 3 sources tracked
Researchers have introduced UniDrive, a novel framework designed to enhance risk understanding in autonomous driving systems by unifying vision-language and grounding capabilities. This approach addresses the limitation…
-
New framework enhances object detection for autonomous driving
Researchers have developed a new framework called Context-Centric Feature Fusion (CCFF) to improve object detection in autonomous driving. This framework uses two attention-based modules: the Local Context Fusion Module…
-
New study analyzes VLM stability for autonomous driving hazard detection
Researchers have developed a new method to analyze the stability of vision-language models (VLMs) used in autonomous driving hazard detection. The study, published on arXiv, proposes using task-aligned stability measure…
-
New LFA method enhances AI error prediction for self-driving cars
Researchers have developed a new method called Layer Feature Attention (LFA) to improve the introspection of 2D object detectors used in automated driving systems. LFA utilizes an attention mechanism to aggregate featur…
-
New FedS2R framework improves autonomous driving segmentation
Researchers have introduced FedS2R, a novel one-shot federated domain generalization framework specifically designed for synthetic-to-real semantic segmentation in autonomous driving. This framework addresses the challe…
-
Edge AI research uses knowledge distillation for robust automotive VRU detection
Researchers have developed a knowledge distillation framework to improve the performance of object detection models on edge hardware for automotive safety. This method trains a smaller YOLOv8-S model to replicate the be…
-
Trust-SSL enhances aerial image self-supervised learning robustness to degradation
Researchers have developed Trust-SSL, a novel self-supervised learning strategy designed to improve the robustness of aerial image analysis. This method introduces a per-sample trust weight into the alignment objective,…