REVIEW 21 cited by
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
read the original abstract
Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue.
Forward citations
Cited by 21 Pith papers
-
nuScenes: A multimodal dataset for autonomous driving
nuScenes provides the first public autonomous-driving dataset that includes synchronized 360-degree data from cameras, radars, and lidar together with 3D bounding-box annotations across 1000 scenes.
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
Steadily moving semi-infinite fracture in plane poroelasticity
A new coupled boundary integral method models steadily moving semi-infinite fractures in plane poroelasticity, solving for mechanical deformation and fluid exchange with verification on analytical test cases.
-
Real-Time Source-Free Object Detection
RT-SFOD adapts dual-head detectors like YOLOv10 for source-free object detection via DHF pseudo-label fusion and MARD loss, delivering 1.4-3.5% mAP gains with 1.3x higher throughput and ~2x fewer parameters than prior...
-
MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
MULTI uses two-stage textual inversion to disentangle camera lens, sensor, view, and domain factors for novel image generation, supporting dataset extension and ControlNet modifications on the new DF-RICO benchmark.
-
Language-Conditioned Visual Grounding with CLIP Multilingual
Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
-
ParkingScenes: A Structured Dataset for End-to-End Autonomous Parking in Simulation Scenes
ParkingScenes is a new multimodal dataset of 704 structured reverse and parallel parking episodes generated in CARLA with Hybrid A* and MPC trajectories, showing better model performance than unstructured simulation data.
-
Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors
Rotation-equivariant convolutions and adaptive TL-Conv layers are added to I2I networks to preserve rotation symmetry and improve translation quality across domains.
-
Learning Under Low Illumination: A Dataset and Algorithm for Traffic Sign Recognition
Introduces the INTSD nighttime traffic sign dataset from India and LENS-Net baseline that performs adaptive illumination-aware detection plus multimodal classification.
-
Segment Any-Quality Images with Generative Latent Space Enhancement
GleSAM integrates latent diffusion into SAM and SAM2 to boost segmentation robustness on low-quality images using minimal extra parameters and a new LQSeg dataset.
-
Steadily moving semi-infinite fracture in plane poroelasticity
XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.
-
Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement
GleSAM++ improves SAM robustness on degraded images by using generative enhancement, feature alignment, and adaptive degradation prediction while adding few parameters.
-
VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning
VIPO improves model-based offline RL by minimizing value function inconsistency between direct data estimates and model predictions, achieving SOTA results on D4RL and NeoRL benchmarks.
-
PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions
PSI is a benchmark dataset for pedestrian intention prediction, driver decision modeling, and reasoning generation in traffic interactions, enriched with human textual explanations.
-
Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Lightweight input adapters preprocess images to match ideal-condition training data for off-the-shelf CV models, enabling self-supervised incremental adaptation and reported gains in segmentation and localization on R...
-
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial...
-
All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles
A survey synthesizing sensor fusion strategies, AV datasets, and emerging LLM/VLM-powered object detection pipelines for autonomous vehicles.
-
How much real data do we actually need: Analyzing object detection performance using synthetic and real data
Synthetic data can partially substitute for real data in object detection training, with performance tied to domain similarity and the volume of real data included.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
-
Deep Learning in the Automotive Industry: Recent Advances and Application Examples
An overview of deep learning applications and challenges in the automotive industry, covering ADAS, automated driving, virtual sensing, and data-driven development.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.