OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

• URL: http://arxiv.org/abs/2407.07844v2
• Date: Mon, 22 Jul 2024 03:26:21 GMT
• Title: OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
• Authors: Hao Wang, Pengzhen Ren, Zequn Jie, Xiao Dong, Chengjian Feng, Yinlong Qian, Lin Ma, Dongmei Jiang, Yaowei Wang, Xiangyuan Lan, Xiaodan Liang,
• Abstract summary: We propose a novel unified open-vocabulary detection method called OV-DINO. It is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmarks.
• Score: 88.59397418187226
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. 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. Specifically, we introduce a Unified Data Integration (UniDI) pipeline to enable end-to-end training and eliminate noise from pseudo-label generation by unifying different data sources into detection-centric data format. In addition, we propose a Language-Aware Selective Fusion (LASF) module to enhance the cross-modality alignment through a language-aware query selection and fusion process. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmarks, achieving state-of-the-art results with an AP of 50.6% on the COCO benchmark and 40.1% on the LVIS benchmark in a zero-shot manner, demonstrating its strong generalization ability. Furthermore, the fine-tuned OV-DINO on COCO achieves 58.4% AP, outperforming many existing methods with the same backbone. The code for OV-DINO is available at https://github.com/wanghao9610/OV-DINO.

Related papers

• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method [108.56493934296687]
  We introduce a divergence-based calibration method, inspired by the divergence-from-randomness concept, to calibrate token probabilities for pretraining data detection. We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
  arXiv  Detail & Related papers  (2024-09-23T07:55:35Z)
• MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection [107.15164718585666]
  We investigate the root cause of VLMs' biased prediction under the open vocabulary detection context. Our observations lead to a simple yet effective paradigm, coded MarvelOVD, that generates significantly better training targets. Our method outperforms the other state-of-the-arts by significant margins.
  arXiv  Detail & Related papers  (2024-07-31T09:23:57Z)
• Generative linguistic representation for spoken language identification [17.9575874225144]
  We explore the utilization of the decoder-based network from the Whisper model to extract linguistic features. We devised two strategies - one based on the language embedding method and the other focusing on direct optimization of LID outputs. We conducted experiments on the large-scale multilingual datasets MLS, VoxLingua107, and CommonVoice to test our approach.
  arXiv  Detail & Related papers  (2023-12-18T06:40:24Z)
• ConNER: Consistency Training for Cross-lingual Named Entity Recognition [96.84391089120847]
  Cross-lingual named entity recognition suffers from data scarcity in the target languages. We propose ConNER as a novel consistency training framework for cross-lingual NER.
  arXiv  Detail & Related papers  (2022-11-17T07:57:54Z)
• Prompt-driven efficient Open-set Semi-supervised Learning [52.30303262499391]
  Open-set semi-supervised learning (OSSL) has attracted growing interest, which investigates a more practical scenario where out-of-distribution (OOD) samples are only contained in unlabeled data. We propose a prompt-driven efficient OSSL framework, called OpenPrompt, which can propagate class information from labeled to unlabeled data with only a small number of trainable parameters.
  arXiv  Detail & Related papers  (2022-09-28T16:25:08Z)
• Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks [18.12933868289846]
  We integrate the linguistic information into the vision-based U-Structure networks designed for salient object detection tasks. We propose a new module called efficient Cross-Modal Self-Attention (eCMSA) to combine visual and linguistic features. To reduce the heavy burden of labeling, we employ a semi-supervised learning method by training an image caption model.
  arXiv  Detail & Related papers  (2022-08-08T18:39:37Z)
• Transducer-based language embedding for spoken language identification [38.60303603000269]
  The acoustic and linguistic features are important cues for the spoken language identification task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. We propose a novel transducer-based language embedding approach for LID tasks by integrating an RNN transducer model into a language embedding framework.
  arXiv  Detail & Related papers  (2022-04-08T07:23:43Z)
• GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation [41.04593978694591]
  Gold technique augments existing data to train better OOS detectors operating in low-data regimes. In experiments across three target benchmarks, the top GOLD model outperforms all existing methods on all key metrics.
  arXiv  Detail & Related papers  (2021-09-07T13:35:03Z)
• AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER [2.739898536581301]
  We design an adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data. We show that the proposed method benefits strongly from this data selection process and outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-04T07:17:18Z)
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [150.07326223077405]
  Few-shot learning is attracting much attention to mitigate data scarcity. We present a discriminative nearest neighbor classification with deep self-attention. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.
  arXiv  Detail & Related papers  (2020-10-25T00:39:32Z)

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.