CP-DETR combines progressive and gated multi-scale prompt-image fusion with text, visual, and optimized prompts to reach state-of-the-art universal detection with one model weight.
OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a "visual vocabulary" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-dataset joint training and generalizes to numerous training datasets without manual label taxonomy merging. We demonstrate superior performance of OmDet over strong baselines in object detection in the wild, open-vocabulary detection, and phrase grounding, achieving state-of-the-art results. Ablation studies reveal the impact of scaling the pre-training visual vocabulary, indicating a promising direction for further expansion to larger datasets. The effectiveness of our deep fusion approach is underscored by its ability to learn jointly from multiple datasets, enhancing performance through knowledge sharing.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection
CP-DETR combines progressive and gated multi-scale prompt-image fusion with text, visual, and optimized prompts to reach state-of-the-art universal detection with one model weight.