mlsanityData to 14 Oct 2026

An Iterative Feedback Mechanism for Improving Natural Language Class Descriptions in Open-Vocabulary Object Detection

arXiv 2503.17285 ↗First posted 21 Mar 2025cs.CV cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced, classes can be defined with natural language text descriptions in the field, immediately before runtime, without needing to retrain the model. We present an approach for improving non-technical users' natural language text descriptions of their desired targets of interest, using a combination of analysis techniques on the text embeddings, and proper combinations of embeddings for contrastive examples. We quantify the improvement that our feedback mechanism provides by demonstrating performance with multiple publicly-available open-vocabulary object detection models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 25 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

23 of 25 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  3. 2022Visual Classification via Description from Large Language Modelscited by 336
  4. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Modelscited by 313
  5. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 267
  6. 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 196
  7. 2024Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)cited by 119
  8. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  9. 2025Vision-Language Models Do Not Understand Negationcited by 72
  10. 2015Part-Stacked CNN for Fine-Grained Visual Categorizationcited by 62
  11. 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
  12. 2022Improving Zero-shot Generalization and Robustness of Multi-modal Modelscited by 45
11 more
  1. 2024LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptorscited by 40
  2. 2024OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervisioncited by 22
  3. 2024Evolving Interpretable Visual Classifiers with Large Language Modelscited by 18
  4. 2024Enhancing Multimodal Understanding with CLIP-Based Image-to-Text Transformationcited by 15
  5. 2024If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptionscited by 14
  6. 2024Multi-modal Attribute Prompting for Vision-Language Modelscited by 12
  7. 2024IntCoOp: Interpretability-Aware Vision-Language Prompt Tuningcited by 5
  8. 2024Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregationcited by 4
  9. 2024Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimizationcited by 3
  10. 2024Quantifying and Enabling the Interpretability of CLIP-like Modelscited by 3
  11. 2024An Application-Agnostic Automatic Target Recognition System Using Vision Language Modelscited by 1

Built on by

Not cited yet.