LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction

• URL: http://arxiv.org/abs/2407.11335v2
• Date: Thu, 18 Jul 2024 07:52:52 GMT
• Title: LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
• Authors: Penghui Du, Yu Wang, Yifan Sun, Luting Wang, Yue Liao, Gang Zhang, Errui Ding, Yan Wang, Jingdong Wang, Si Liu,
• Abstract summary: Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs) We propose the Language Model Instruction (LaMI) strategy, which leverages the relationships between visual concepts and applies them within a simple yet effective DETR-like detector.
• Score: 63.668635390907575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP.However, two main challenges emerge:(1) A deficiency in concept representation, where the category names in CLIP's text space lack textual and visual knowledge.(2) An overfitting tendency towards base categories, with the open vocabulary knowledge biased towards base categories during the transfer from VLMs to detectors.To address these challenges, we propose the Language Model Instruction (LaMI) strategy, which leverages the relationships between visual concepts and applies them within a simple yet effective DETR-like detector, termed LaMI-DETR.LaMI utilizes GPT to construct visual concepts and employs T5 to investigate visual similarities across categories.These inter-category relationships refine concept representation and avoid overfitting to base categories.Comprehensive experiments validate our approach's superior performance over existing methods in the same rigorous setting without reliance on external training resources.LaMI-DETR achieves a rare box AP of 43.4 on OV-LVIS, surpassing the previous best by 7.8 rare box AP.

Related papers

• Open-Vocabulary Temporal Action Localization using Multimodal Guidance [67.09635853019005]
  OVTAL enables a model to recognize any desired action category in videos without the need to explicitly curate training data for all categories. This flexibility poses significant challenges, as the model must recognize not only the action categories seen during training but also novel categories specified at inference. We introduce OVFormer, a novel open-vocabulary framework extending ActionFormer with three key contributions.
  arXiv  Detail & Related papers  (2024-06-21T18:00:05Z)
• Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection [101.15777242546649]
  Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from pre-trained large-scale vision-language models to the task of object detection. We present a novel OVD framework termed LBP to propose learning background prompts to harness explored implicit background knowledge.
  arXiv  Detail & Related papers  (2024-06-01T17:32:26Z)
• Anomaly Detection by Adapting a pre-trained Vision Language Model [48.225404732089515]
  We present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. We introduce the learnable prompt and propose to associate it with abnormal patterns through self-supervised learning. We achieve the state-of-the-art 97.5/55.6 and 89.3/33.1 on MVTec-AD and VisA for anomaly detection and localization.
  arXiv  Detail & Related papers  (2024-03-14T15:35:07Z)
• Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning [23.671999163027284]
  This paper proposes a novel framework for multi-label image recognition without any training data. It uses knowledge of pre-trained Large Language Model to learn prompts to adapt pretrained Vision-Language Model like CLIP to multilabel classification. Our framework presents a new way to explore the synergies between multiple pre-trained models for novel category recognition.
  arXiv  Detail & Related papers  (2024-03-02T13:43:32Z)
• OV-VG: A Benchmark for Open-Vocabulary Visual Grounding [33.02137080950678]
  This research endeavor introduces novel and challenging open-vocabulary visual tasks. The overarching aim is to establish connections between language descriptions and the localization of novel objects. We have curated a benchmark, encompassing 7,272 OV-VG images and 1,000 OV-PL images.
  arXiv  Detail & Related papers  (2023-10-22T17:54:53Z)
• Multi-Modal Classifiers for Open-Vocabulary Object Detection [104.77331131447541]
  The goal of this paper is open-vocabulary object detection (OVOD) We adopt a standard two-stage object detector architecture. We explore three ways via: language descriptions, image exemplars, or a combination of the two.
  arXiv  Detail & Related papers  (2023-06-08T18:31:56Z)
• Multi-modal Queried Object Detection in the Wild [72.16067634379226]
  MQ-Det is an efficient architecture and pre-training strategy design for real-world object detection. It incorporates vision queries into existing language-queried-only detectors. MQ-Det's simple yet effective architecture and training strategy design is compatible with most language-queried object detectors.
  arXiv  Detail & Related papers  (2023-05-30T12:24:38Z)
• Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization [73.14053674836838]
  Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary. Recent work resorts to the rich knowledge in pre-trained vision-language models. We present MEDet, a novel OVD framework with proposal mining and prediction equalization.
  arXiv  Detail & Related papers  (2022-06-22T14:30:41Z)

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.