Zero-Shot Object Detection
35 papers with code • 7 benchmarks • 6 datasets
Zero-shot object detection (ZSD) is the task of object detection where no visual training data is available for some of the target object classes.
( Image credit: Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts )
Benchmarks
These leaderboards are used to track progress in Zero-Shot Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Zero-Shot Object Detection models and implementations
MS COCO
LVIS
PASCAL VOC 2007
MSCOCO
RF100
Most implemented papers
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
idea-research/groundingdino
•
•
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.
Learning Open-World Object Proposals without Learning to Classify
mcahny/object_localization_network
•
•
In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
Zero-Shot Instance Segmentation
zhengye1995/Zero-shot-Instance-Segmentation
•
•
CVPR 2021
We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI).
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
On COCO, ViLD outperforms the previous state-of-the-art by 4. 8 on novel AP and 11. 4 on overall AP.
Polarity Loss for Zero-shot Object Detection
This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes.
Grounded Language-Image Pre-training
The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich.
Scaling Open-Vocabulary Object Detection
google-research/scenic
•
•
NeurIPS 2023
However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31. 2% to 44. 6% (43% relative improvement).
YOLO-World: Real-Time Open-Vocabulary Object Detection
ailab-cvc/yolo-world
•
•
CVPR 2024
The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools.
Zero-Shot Object Detection by Hybrid Region Embedding
Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images.
