Zero-Shot Object Detection

18 papers with code • 5 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 )

Most implemented papers

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

computer-vision-in-the-wild/cvinw_readings 19 Apr 2022

In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.

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

tensorflow/tpu ICLR 2022

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

KennithLi/Awesome-Zero-Shot-Object-Detection 22 Nov 2018

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.

Zero-Shot Object Detection by Hybrid Region Embedding

KennithLi/Awesome-Zero-Shot-Object-Detection 16 May 2018

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.

Synthesizing the Unseen for Zero-shot Object Detection

nasir6/zero_shot_detection 19 Oct 2020

The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference.

Learning Open-World Object Proposals without Learning to Classify

mcahny/object_localization_network 15 Aug 2021

In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.

Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection

hanoonaR/object-centric-ovd 7 Jul 2022

Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision.

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

idea-research/groundingdino 9 Mar 2023

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.

Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts

salman-h-khan/ZSD_Release 16 Mar 2018

We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear only as a part of a complex scene, warranting both the `recognition' and `localization' of an unseen category.