Zero-Shot Object Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 39 papers with code (57 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
  9 Mar 2023 10 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  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…
• ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
  19 Apr 2022 9 repositories listed Syntology ran 4 of 20 samples · 16 unverified
  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
  15 Aug 2021 6 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
• Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
  28 Apr 2021 4 repositories listed
  On COCO, ViLD outperforms the previous state-of-the-art by 4.
• Zero-Shot Instance Segmentation
  14 Apr 2021 4 repositories listed
  We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI).
• VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
  17 May 2025 3 repositories listed Syntology ran 1 of 15 samples · 14 unverified
  Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks.
• Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
  16 May 2024 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Empirical results demonstrate the effectiveness of Grounding DINO 1.
• YOLO-World: Real-Time Open-Vocabulary Object Detection
  30 Jan 2024 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools.
• Scaling Open-Vocabulary Object Detection
  16 Jun 2023 3 repositories listed
  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…
• Grounded Language-Image Pre-training
  7 Dec 2021 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  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…
• Polarity Loss for Zero-shot Object Detection
  22 Nov 2018 3 repositories listed
  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.
• T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
  21 Mar 2024 2 repositories listed
  Recognizing the complementary strengths and weaknesses of both text and visual prompts, we introduce T-Rex2 that synergizes both prompts within a single model through contrastive learning.
• Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head
  11 Mar 2024 2 repositories listed
  End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities.
• Efficient Feature Distillation for Zero-shot Annotation Object Detection
  21 Mar 2023 2 repositories listed
  We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD).
• Synthesizing the Unseen for Zero-shot Object Detection
  19 Oct 2020 2 repositories listed
  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.
• Zero-Shot Object Detection by Hybrid Region Embedding
  16 May 2018 2 repositories listed
  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.
• Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving Safety
  18 Apr 2025 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  To assess model performance, we create a ground truth dataset by denoising and extending the foundational COOOL (Challenge-of-Out-of-Label) anomaly detection benchmark dataset with complete natural language descriptions…
• LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset
  4 Mar 2025 1 repository listed
  We propose a zero-shot method that combines background subtraction, zero-shot object detection, filtering, and segmentation to leverage this dataset.
• No Annotations for Object Detection in Art through Stable Diffusion
  9 Dec 2024 1 repository listed
  Object detection in art is a valuable tool for the digital humanities, as it allows for faster identification of objects in artistic and historical images compared to humans.
• Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects
  3 Dec 2024 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  While adversarial attacks on object detection models are well-studied for 2D images, their impact on 3D models remains underexplored.
• DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
  21 Nov 2024 1 repository listed
  DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.
• OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
  10 Jul 2024 1 repository listed
  To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework.
• OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
  28 May 2024 1 repository listed Syntology ran 9 of 11 samples · 2 unverified
  However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence to trained categories and confuse novel categories with the background.
• DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM
  19 Mar 2024 1 repository listed
  We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini.
• Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection
  14 Feb 2024 1 repository listed
  The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories.
• SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
  7 Oct 2023 1 repository listed
  To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
• ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data
  22 Aug 2023 1 repository listed Syntology ran 1 of 4 samples · 3 unverified
  The first key contribution of this work is to demonstrate through systematic evaluations that as the pairwise complexity of the training dataset increases, standard VLMs struggle to learn region-attribute relationships,…
• Multi-modal Queried Object Detection in the Wild
  30 May 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified
  To address the learning inertia problem brought by the frozen detector, a vision conditioned masked language prediction strategy is proposed.
• DoUnseen: Tuning-Free Class-Adaptive Object Detection of Unseen Objects for Robotic Grasping
  6 Apr 2023 1 repository listed
  In this work, we are interested in open sets where the number of classes is unknown, varying, and without pre-knowledge about the objects' types.
• ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
  26 Mar 2023 1 repository listed Syntology ran 5 of 9 samples · 4 unverified
  However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.