ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness

• URL: http://arxiv.org/abs/2608.06841v1
• Date: Fri, 07 Aug 2026 06:01:06 GMT
• Title: ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness
• Abstract summary: We formulate Expanded Class-Agnostic Detection (ECAD), a new setting that aims to discover category-agnostic visual candidates.<n>ECADet is a lightweight DETR-based detector built upon a frozen DINOv3 encoder.<n>We show that ECADet consistently outperforms representative class-agnostic and proposal-based detectors on BTCO-Bench.
• Score: 19.94019125942239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and interaction. However, existing detection paradigms largely inherit a thing-centric notion of objectness, where detectors are mainly trained to localize discrete and countable object instances. Consequently, many semantically meaningful visual elements, such as sky, road, grassland, water, and sports courts, are often absorbed into the background despite their importance for scene understanding and spatial reasoning. In this paper, we formulate Expanded Class-Agnostic Detection (ECAD), a new setting that aims to discover category-agnostic visual candidates beyond conventional thing-centric objects. To support this setting, we construct BTCO-Bench, a Beyond Thing-Centric Objectness benchmark with category-agnostic box annotations covering both real-world and cross-domain scenarios. We further propose ECADet, a lightweight DETR-based detector built upon a frozen DINOv3 encoder, and introduce Geometry-Aware Expert Regression (GAER) and Prototype-Guided Query Modulation (PGQM) to improve localization and objectness estimation for diverse visual elements, respectively. Extensive experiments show that ECADet consistently outperforms representative class-agnostic and proposal-based detectors on BTCO-Bench, demonstrating the effectiveness of expanded objectness discovery. Code and benchmark will be released.

Related papers

• Background-Free Objectness Learning for Class-Agnostic Detection [1.423280626666929]
  Background-Free Objectness Learning (B-FOR) learns objectness without explicit background supervision on unlabeled regions.<n> Supervision is confined to reliable annotated regions through spatially structured soft targets.<n>B-FOR improves recall by more than +10 AR points over prior class-agnostic baselines.
  arXiv  Detail & Related papers  (2026-08-29T12:39:23Z)
• Hierarchical Fine-Grained Aerial Object Detection [41.39072956799442]
  We present ExpertDet, a scheme that incorporates expert-informed cues to enhance fine-grained aerial object detection.<n>Specifically, we design Vision-aware Masked Attribute Modeling (VMAM), which aligns semantics with visual structures.<n>We also propose Hierarchical Visual Instance Promotion (HierVIP), which builds a visual prototype tree based on hierarchical relations.
  arXiv  Detail & Related papers  (2026-06-15T09:20:16Z)
• SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection [12.404050551208366]
  Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts.<n>We construct a benchmark named OVCOD-D by augmenting carefully selected camouflaged object images with fine-grained textual descriptions.<n>Under the open-set evaluation setting, the proposed method achieves an AP of 56.4 on the OVCOD-D benchmark.
  arXiv  Detail & Related papers  (2026-03-27T06:37:32Z)
• From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning [71.41062111470414]
  Current object detectors excel at entity localization and classification, yet exhibit inherent limitations in event recognition capabilities.<n>We present a novel framework that expands the capability of standard object detectors beyond mere object recognition to complex event understanding.<n>Our key innovation lies in bridging the semantic gap between object detection and event understanding without requiring expensive task-specific training.
  arXiv  Detail & Related papers  (2025-02-09T10:30:54Z)
• Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation [58.37525311718006]
  We put forth a novel formulation of the aerial object detection problem, namely open-vocabulary aerial object detection (OVAD) We propose CastDet, a CLIP-activated student-teacher detection framework that serves as the first OVAD detector specifically designed for the challenging aerial scenario. Our framework integrates a robust localization teacher along with several box selection strategies to generate high-quality proposals for novel objects.
  arXiv  Detail & Related papers  (2024-11-04T12:59:13Z)
• Detecting Every Object from Events [24.58024539462497]
  We propose Detecting Every Object in Events (DEOE), an approach tailored for achieving high-speed, class-agnostic open-world object detection in event-based vision. Our code is available at https://github.com/Hatins/DEOE.
  arXiv  Detail & Related papers  (2024-04-08T08:20:53Z)
• GOOD: Towards Domain Generalized Orientated Object Detection [37.53218059792163]
  Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution.<n>We propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains.
  arXiv  Detail & Related papers  (2024-02-20T07:12:22Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
  We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs. We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
  arXiv  Detail & Related papers  (2021-12-21T17:10:21Z)
• Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
  We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object. This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
  arXiv  Detail & Related papers  (2021-08-15T14:36:02Z)
• Robust Object Detection via Instance-Level Temporal Cycle Confusion [89.1027433760578]
  We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf) For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision.
  arXiv  Detail & Related papers  (2021-04-16T21:35:08Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.