# Class-agnostic Object Detection

arXiv: https://arxiv.org/abs/2011.14204 · HTML: https://mlsanity.com/paper/2011.14204/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2020.

## Built on by (most cited first, 17 of 17)

- [Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation](https://mlsanity.com/paper/2104.04691/) (2021)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Open-World Entity Segmentation](https://mlsanity.com/paper/2107.14228/) (2021)
- [MobileSAMv2: Faster Segment Anything to Everything](https://mlsanity.com/paper/2312.09579/) (2023)
- [CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2307.16634/) (2023)
- [Learning to Detect Every Thing in an Open World](https://mlsanity.com/paper/2112.01698/) (2021)
- [Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection](https://mlsanity.com/paper/2306.14291/) (2023)
- [DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection](https://mlsanity.com/paper/2406.14924/) (2024)
- [GOOD: Exploring Geometric Cues for Detecting Objects in an Open World](https://mlsanity.com/paper/2212.11720/) (2022)
- [Meta-Point Learning and Refining for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2403.13647/) (2024)
- [SOHES: Self-supervised Open-world Hierarchical Entity Segmentation](https://mlsanity.com/paper/2404.12386/) (2024)
- [ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos](https://mlsanity.com/paper/2407.12987/) (2024)
- [CatFree3D: Category-agnostic 3D Object Detection with Diffusion](https://mlsanity.com/paper/2408.12747/) (2024)
- [FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery](https://mlsanity.com/paper/2404.02877/) (2024)
- [REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling](https://mlsanity.com/paper/2607.03004/) (2026)
- [ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness](https://mlsanity.com/paper/2608.06841/) (2026)
- [Background-Free Objectness Learning for Class-Agnostic Detection](https://mlsanity.com/paper/2608.29232/) (2026)

## Abstract (arXiv)

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a limited number of object types with unknown objects treated as background content. This hinders the adoption of conventional detectors in real-world applications like large-scale object matching, visual grounding, visual relation prediction, obstacle detection (where it is more important to determine the presence and location of objects than to find specific types), etc. We propose class-agnostic object detection as a new problem that focuses on detecting objects irrespective of their object-classes. Specifically, the goal is to predict bounding boxes for all objects in an image but not their object-classes. The predicted boxes can then be consumed by another system to perform application-specific classification, retrieval, etc. We propose training and evaluation protocols for benchmarking class-agnostic detectors to advance future research in this domain. Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions. Experimental results show that adversarial learning improves class-agnostic detection efficacy.