Semantically-Guided Domain Randomization (S-GDR), an annotation-free adaptation pipeline that couples Vision-Language Model (VLM)-based semantic captioning of a small unannotated real reference set with diffusion-based background synthesis with diffusion-based background synthesis (Stable Diffusion XL conditioned by ControlNet and IP-Adapter), is evaluated.
Abstract
Retraining visual perception pipelines in High-Mix, Low-Volume (HMLV) automotive manufacturing must be carried out under tight annotation, energy, and time budgets, yet most Synthetic Data Generation (SDG) strategies still operate in the thousands of images. This work evaluates Semantically-Guided Domain Randomization (S-GDR), an annotation-free adaptation pipeline that couples Vision-Language Model (VLM)-based semantic captioning of a small unannotated real reference set with diffusion-based background synthesis (Stable Diffusion XL (SDXL) conditioned by ControlNet and IP-Adapter) and mask-based object composition. On an automotive multi-object detection benchmark and with a fixed budget of 200 synthetic training images, S-GDR reaches mAP50-95 = 0.739 on a real held-out test set, outperforming a domain-randomized render baseline (mAP50-95 = 0.697) as well as brightness filtering, perceptual hashing, CycleGAN style transfer, and unguided diffusion variants sharing the same 200-image budget. These initial observations position S-GDR as a promising annotation- free alternative for extreme data-scarcity regimes.
Unsupervised Domain Adaptation (UDA) for object detection remains challenging under adverse weather due to significant distribution shifts. While recent Vision Foundation Model (VFM) based methods show promise, they often encounter limitations in extreme domain gaps and pseudo-label noise. This paper proposes two enhan...
T. Doan, D. C. Bui, Khanh-Duy Nguyen et al.· International Conference on...· 0 citations
This work presents a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization, and generalizes to any detection-classification edge pipeline.
This study introduces ProbeGen, a benchmark for zero-shot generative perception that casts monocular depth estimation, referring/reasoning segmentation, and object counting as conditional generation tasks specified through text prompts, and compares 20 models in total.
G2D is proposed, a training-free framework that uses a generative VLM to verify CLIP-retrieved candidates against the image and transfers to DCLIP, WaffleCLIP, and CuPL, supporting a practical interface between discriminative proposal and generative visual reasoning.
Zehua Hao, Fang Liu, Qinliang Wang et al.· 0 citations
This work presents AQ3D, which is designed to handle scenes of various sizes during training and inference and sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation.
Keno Moenck, T. Schüppstuhl· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Enforcing physics-based constraints prevents AI models from generating unreliable predictions for complex nonlinear systems in weather, climate, and turbulent flows.
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.