Pith. sign in

REVIEW 2 major objections 2 minor 65 references

Scene graphs enable better detection of novel object categories in open-vocabulary settings by modeling their relationships.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-28 01:53 UTC pith:P3RMS6YR

load-bearing objection Scene graphs for OVOD add a plausible relational angle but the base-class dependency in graph building creates a real circularity risk for novel categories, and the abstract gives no numbers to check the claims. the 2 major comments →

arxiv 2606.05916 v1 pith:P3RMS6YR submitted 2026-06-04 cs.CV

Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs

Yi Chen , Yinghao Lu , Zhehao Li , Chenchen Yan , Jiafei Wu , Chong Wang , Jiangbo Qian This is my paper
classification cs.CV
keywords open vocabulary object detectionscene graphsrelational modelingnovel object categoriesknowledge distillationvision language modelsCOCOLVIS
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to demonstrate that current open-vocabulary object detection methods, which rely on knowledge from vision-language models, fall short because they ignore structured relationships like object interactions and spatial arrangements within specific images. It introduces a framework that generates scene graphs to represent these relationships between regions, uses a relation attention module to emphasize important cues, and adds a textual alignment branch from captions to integrate semantic knowledge. If correct, this would mean that explicitly incorporating image-specific relational information leads to improved accuracy when identifying objects not seen during training. Readers would care because open-vocabulary detection is essential for systems that must recognize new items in dynamic environments without additional labeled data.

Core claim

The Scene-guided Relational Modeling detection framework utilizes scene graphs to capture structured semantic and spatial relationships between candidate regions and their contextual objects, models interactions among neighboring regions, incorporates a Relation Attention Module to amplify key relational cues, and uses a scene-based textual alignment branch to distill category knowledge from captions, resulting in superior performance on novel categories compared to other open-vocabulary object detection methods on the COCO and LVIS datasets.

What carries the argument

The scene graph that represents semantic and spatial relationships between candidate regions and contextual objects, combined with the Relation Attention Module and scene-based textual alignment branch.

Load-bearing premise

Scene graphs generated from the image provide accurate and useful relational information that directly aids in detecting novel object categories.

What would settle it

A controlled experiment where the scene graph and relation attention components are removed from the model, and no significant drop in AP for novel categories on COCO or LVIS is observed.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Improved AP for novel categories on COCO and LVIS datasets over existing OVOD methods.
  • Explicit modeling of interactions and spatial arrangements between objects aids in detecting unseen categories.
  • Distillation of knowledge from captions guides relational alignment between visual and semantic information.
  • Overlooking structured relationships in images restricts the effectiveness of prior knowledge distillation approaches.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar relational modeling might benefit other tasks involving object interactions, such as visual question answering.
  • Advancements in automatic scene graph generation could further enhance this framework's results.
  • The approach suggests that image-specific context is more valuable than general pre-trained knowledge alone for novel object recognition.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 2 minor

Summary. The paper proposes a Scene-guided Relational Modeling framework for open-vocabulary object detection. It uses scene graphs to capture semantic and spatial relationships between candidate regions and contextual objects, introduces a Relation Attention Module to amplify key relational cues, and adds a scene-based textual alignment branch that distills category knowledge from captions. The central claim is that this yields superior AP on novel categories compared to prior OVOD methods on the COCO and LVIS datasets.

Significance. If the performance claims hold after proper verification, the work would represent a useful step in OVOD by explicitly incorporating structured relational context from scene graphs, an aspect often missing from pure knowledge-distillation baselines. The combination of visual relation modeling with caption-based alignment could help address cases where novel objects benefit from neighborhood context.

major comments (2)
  1. [Abstract] Abstract: the claim that the model 'achieves superior performance' and 'improving the AP for novel categories on COCO and LVIS' is presented without any quantitative results, baselines, dataset splits, error bars, or implementation details. This absence makes the central empirical claim unverifiable and is load-bearing for acceptance.
  2. [Method (scene graph and Relation Attention Module)] Scene-graph construction (described in the method): scene graphs are typically produced by off-the-shelf parsers trained exclusively on base categories. Novel objects therefore appear only as background or are omitted entirely from the graph. The Relation Attention Module and scene-based textual alignment cannot recover relational cues for objects absent from the input graph, so any reported gain on novel splits may be driven by the caption-distillation branch rather than the claimed relational modeling.
minor comments (2)
  1. [Method] Notation for the scene graph and the Relation Attention Module should be defined more explicitly (e.g., how nodes and edges are represented and how attention weights are computed).
  2. [Abstract] The abstract states that 'overlooking structured relationships significantly restricts effectiveness' but provides no supporting citation or preliminary experiment; a brief reference to prior OVOD work that ignores relations would strengthen the motivation.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the two major comments point-by-point below, agreeing where changes are needed and providing clarifications on the method.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the model 'achieves superior performance' and 'improving the AP for novel categories on COCO and LVIS' is presented without any quantitative results, baselines, dataset splits, error bars, or implementation details. This absence makes the central empirical claim unverifiable and is load-bearing for acceptance.

    Authors: We agree that the abstract should include concrete quantitative results to support the performance claims. In the revised manuscript we will update the abstract to report specific AP improvements on novel categories for both COCO and LVIS, name the main baselines, note the standard novel/base splits, and reference error bars where applicable. revision: yes

  2. Referee: [Method (scene graph and Relation Attention Module)] Scene-graph construction (described in the method): scene graphs are typically produced by off-the-shelf parsers trained exclusively on base categories. Novel objects therefore appear only as background or are omitted entirely from the graph. The Relation Attention Module and scene-based textual alignment cannot recover relational cues for objects absent from the input graph, so any reported gain on novel splits may be driven by the caption-distillation branch rather than the claimed relational modeling.

    Authors: We acknowledge the limitation of off-the-shelf scene-graph parsers. Our Relation Attention Module nevertheless operates on the full set of candidate regions produced by the detector (which include potential novel objects) and uses the graph to propagate contextual cues from neighboring base-category objects. The scene-based textual alignment branch supplies complementary supervision. We will revise the method section to clarify the exact scene-graph construction pipeline and add ablation experiments that isolate the relational-modeling contribution from the caption-distillation branch alone. revision: partial

Circularity Check

0 steps flagged

No circularity; method integrates external pre-trained components with new modules without self-referential reduction.

full rationale

The abstract and description present a framework that utilizes scene graphs from external sources, a Relation Attention Module, and scene-based textual alignment distilled from captions, all built on pre-trained vision-language models. No equations, self-citations, or derivations are shown that reduce the claimed AP improvements on novel categories to fitted inputs or prior author results by construction. The performance claims are framed as empirical outcomes from experiments on COCO and LVIS, making the derivation self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the effectiveness of scene graph representations and the new modules, which depend on external pre-trained models whose quality is assumed but not derived here.

axioms (2)
  • domain assumption Pre-trained vision-language models contain transferable knowledge useful for novel object categories
    Invoked as the base for knowledge distillation in the proposed framework.
  • domain assumption Scene graphs can be reliably generated to capture semantic and spatial relationships between objects
    Central premise for the Scene-guided Relational Modeling approach.

pith-pipeline@v0.9.1-grok · 5722 in / 1371 out tokens · 40701 ms · 2026-06-28T01:53:34.529937+00:00 · methodology

0 comments
read the original abstract

Open-vocabulary object detection seeks to identify novel object categories that were not part of the training data. Many knowledge distillation-based approaches have shown promising performance by transferring knowledge from pre-trained vision-language models to object detection. However, these methods often overlook structured, image-specific relationships between objects, such as interactions and spatial arrangements. This oversight can significantly restrict the effectiveness of detecting novel categories. To address this issue, we propose a Scene-guided Relational Modeling detection framework. This framework utilizes scene graphs to capture structured semantic and spatial relationships between candidate regions and their contextual objects. It explicitly models interactions among neighboring regions and incorporates a Relation Attention Module to implicitly amplify the key relational cues extracted from the scene graph. Furthermore, we present a scene-based textual alignment branch that distills category knowledge from captions to guide relational alignment. This approach facilitates a seamless integration of visual relations with semantic information for enhanced detection performance. Comprehensive experiments show that our model achieves superior performance compared to other OVOD methods, improving the AP for novel categories on COCO and LVIS datasets.

Figures

Figures reproduced from arXiv: 2606.05916 by Chenchen Yan, Chong Wang, Jiafei Wu, Jiangbo Qian, Yi Chen, Yinghao Lu, Zhehao Li.

Figure 1
Figure 1. Figure 1: (a) Previous works adopt various region partitioning strategies to [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The overall architecture of the Scene-guided Relational Modeling (SRM) detection framework. It explicitly models and enhances the interactive [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Ablation study on the number of sampled groups (Top- [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results to show the effectiveness of the NR [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative comparison results on OV-COCO. For each group, red boxes indicate the novel categories and the feature map responses to queried novel [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

65 extracted references · 8 canonical work pages · 6 internal anchors

  1. [1]

    Faster r-cnn: Towards real-time object detection with region proposal networks,

    S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,”Advances in neural information processing systems, vol. 28, 2015

    2015

  2. [2]

    Attention is all you need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,”Advances in neural information processing systems, vol. 30, 2017

    2017

  3. [3]

    End-to-end object detection with transformers,

    N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-end object detection with transformers,” in European conference on computer vision. Springer, 2020, pp. 213– 229

    2020

  4. [4]

    Localized vision-language match- ing for open-vocabulary object detection,

    M. A. Bravo, S. Mittal, and T. Brox, “Localized vision-language match- ing for open-vocabulary object detection,” inDAGM German Conference on Pattern Recognition. Springer, 2022, pp. 393–408

    2022

  5. [5]

    Detecting twenty-thousand classes using image-level supervision,

    X. Zhou, R. Girdhar, A. Joulin, P. Kr ¨ahenb¨uhl, and I. Misra, “Detecting twenty-thousand classes using image-level supervision,” inEuropean Conference on Computer Vision. Springer, 2022, pp. 350–368

    2022

  6. [6]

    Learning object-language alignments for open-vocabulary object detection,

    C. Lin, P. Sun, Y . Jiang, P. Luo, L. Qu, G. Haffari, Z. Yuan, and J. Cai, “Learning object-language alignments for open-vocabulary object detection,”arXiv preprint arXiv:2211.14843, 2022

    work page arXiv 2022

  7. [7]

    Ex- ploring region-word alignment in built-in detector for open-vocabulary object detection,

    H. Zhang, Q. Zhao, L. Zheng, H. Zeng, Z. Ge, T. Li, and S. Xu, “Ex- ploring region-word alignment in built-in detector for open-vocabulary object detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 16 975–16 984

    2024

  8. [8]

    Contrastive feature masking open-vocabulary vision transformer,

    D. Kim, A. Angelova, and W. Kuo, “Contrastive feature masking open-vocabulary vision transformer,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 15 602–15 612

    2023

  9. [9]

    Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

    X. Gu, T.-Y . Lin, W. Kuo, and Y . Cui, “Open-vocabulary object detection via vision and language knowledge distillation,”arXiv preprint arXiv:2104.13921, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  10. [10]

    Aligning bag of regions for open-vocabulary object detection,

    S. Wu, W. Zhang, S. Jin, W. Liu, and C. C. Loy, “Aligning bag of regions for open-vocabulary object detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15 254–15 264

    2023

  11. [11]

    Learning background prompts to discover implicit knowledge for open vocabulary object detection,

    J. Li, J. Zhang, J. Li, G. Li, S. Liu, L. Lin, and G. Li, “Learning background prompts to discover implicit knowledge for open vocabulary object detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 16 678–16 687

    2024

  12. [12]

    Conceptnet 5.5: An open multilingual graph of general knowledge,

    R. Speer, J. Chin, and C. Havasi, “Conceptnet 5.5: An open multilingual graph of general knowledge,” inProceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017

    2017

  13. [13]

    Visual relationship detection with language priors,

    C. Lu, R. Krishna, M. Bernstein, and L. Fei-Fei, “Visual relationship detection with language priors,” inComputer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer, 2016, pp. 852–869

    2016

  14. [14]

    You only look once: Unified, real-time object detection,

    J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779– 788

    2016

  15. [15]

    Mask r-cnn,

    K. He, G. Gkioxari, P. Doll ´ar, and R. Girshick, “Mask r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–2969

    2017

  16. [16]

    Sparse r-cnn: End-to-end object detection with learnable proposals,

    P. Sun, R. Zhang, Y . Jiang, T. Kong, C. Xu, W. Zhan, M. Tomizuka, L. Li, Z. Yuan, C. Wanget al., “Sparse r-cnn: End-to-end object detection with learnable proposals,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 14 454–14 463

    2021

  17. [17]

    Zero- shot object detection,

    A. Bansal, K. Sikka, G. Sharma, R. Chellappa, and A. Divakaran, “Zero- shot object detection,” inProceedings of the European conference on computer vision (ECCV), 2018, pp. 384–400

    2018

  18. [18]

    Zero-Shot Object Detection by Hybrid Region Embedding

    B. Demirel, R. G. Cinbis, and N. Ikizler-Cinbis, “Zero-shot object de- tection by hybrid region embedding,”arXiv preprint arXiv:1805.06157, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  19. [19]

    Synthesizing the unseen for zero-shot object detection,

    N. Hayat, M. Hayat, S. Rahman, S. Khan, S. W. Zamir, and F. S. Khan, “Synthesizing the unseen for zero-shot object detection,” inProceedings of the Asian conference on computer vision, 2020

    2020

  20. [20]

    Transductive learning for zero- shot object detection,

    S. Rahman, S. Khan, and N. Barnes, “Transductive learning for zero- shot object detection,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6082–6091

    2019

  21. [21]

    Don’t even look once: Synthesizing features for zero-shot detection,

    P. Zhu, H. Wang, and V . Saligrama, “Don’t even look once: Synthesizing features for zero-shot detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 693–11 702

    2020

  22. [22]

    Gtnet: Gen- erative transfer network for zero-shot object detection,

    S. Zhao, C. Gao, Y . Shao, L. Li, C. Yu, Z. Ji, and N. Sang, “Gtnet: Gen- erative transfer network for zero-shot object detection,” inProceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, 2020, pp. 12 967–12 974

    2020

  23. [23]

    Object-aware distillation pyramid for open-vocabulary object detection,

    L. Wang, Y . Liu, P. Du, Z. Ding, Y . Liao, Q. Qi, B. Chen, and S. Liu, “Object-aware distillation pyramid for open-vocabulary object detection,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 11 186–11 196

    2023

  24. [24]

    Learning transferable visual models from natural language supervision,

    A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clarket al., “Learning transferable visual models from natural language supervision,” inInternational conference on machine learning. PMLR, 2021, pp. 8748–8763

    2021

  25. [25]

    Scaling up visual and vision-language representation learning with noisy text supervision,

    C. Jia, Y . Yang, Y . Xia, Y .-T. Chen, Z. Parekh, H. Pham, Q. Le, Y .-H. Sung, Z. Li, and T. Duerig, “Scaling up visual and vision-language representation learning with noisy text supervision,” inInternational conference on machine learning. PMLR, 2021, pp. 4904–4916

    2021

  26. [26]

    Learning visual features from large weakly supervised data,

    A. Joulin, L. Van Der Maaten, A. Jabri, and N. Vasilache, “Learning visual features from large weakly supervised data,” inComputer Vision– ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14. Springer, 2016, pp. 67–84

    2016

  27. [27]

    Learning visual n-grams from web data,

    A. Li, A. Jabri, A. Joulin, and L. Van Der Maaten, “Learning visual n-grams from web data,” inProceedings of the IEEE International Conference on Computer Vision, 2017, pp. 4183–4192

    2017

  28. [28]

    Imagenet: A large-scale hierarchical image database,

    J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255

    2009

  29. [29]

    Groupvit: Semantic segmentation emerges from text supervision,

    J. Xu, S. De Mello, S. Liu, W. Byeon, T. Breuel, J. Kautz, and X. Wang, “Groupvit: Semantic segmentation emerges from text supervision,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18 134–18 144

    2022

  30. [30]

    Language-driven Semantic Segmentation

    B. Li, K. Q. Weinberger, S. Belongie, V . Koltun, and R. Ranftl, “Language-driven semantic segmentation,”arXiv preprint arXiv:2201.03546, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  31. [31]

    Extract free dense labels from clip,

    C. Zhou, C. C. Loy, and B. Dai, “Extract free dense labels from clip,” inEuropean Conference on Computer Vision. Springer, 2022, pp. 696– 712

    2022

  32. [32]

    Scene graph generation by iterative message passing,

    D. Xu, Y . Zhu, C. B. Choy, and L. Fei-Fei, “Scene graph generation by iterative message passing,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5410–5419

    2017

  33. [33]

    Integrating object-aware and interaction-aware knowledge for weakly supervised scene graph generation,

    X. Li, L. Chen, W. Ma, Y . Yang, and J. Xiao, “Integrating object-aware and interaction-aware knowledge for weakly supervised scene graph generation,” inProceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 4204–4213

    2022

  34. [34]

    Bipartite graph network with adaptive message passing for unbiased scene graph generation,

    R. Li, S. Zhang, B. Wan, and X. He, “Bipartite graph network with adaptive message passing for unbiased scene graph generation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11 109–11 119. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 10

    2021

  35. [35]

    Sgtr: End-to-end scene graph generation with transformer,

    R. Li, S. Zhang, and X. He, “Sgtr: End-to-end scene graph generation with transformer,” inproceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 19 486–19 496

    2022

  36. [36]

    vtgraphnet: Learning weakly-supervised scene graph for complex visual grounding,

    F. Lyu, W. Feng, and S. Wang, “vtgraphnet: Learning weakly-supervised scene graph for complex visual grounding,”Neurocomputing, vol. 413, pp. 51–60, 2020

    2020

  37. [37]

    Structure inference net: Object detection using scene-level context and instance-level relationships,

    Y . Liu, R. Wang, S. Shan, and X. Chen, “Structure inference net: Object detection using scene-level context and instance-level relationships,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 6985–6994

    2018

  38. [38]

    Graph-structured referring expression reasoning in the wild,

    S. Yang, G. Li, and Y . Yu, “Graph-structured referring expression reasoning in the wild,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 9952–9961

    2020

  39. [39]

    Towards open-vocabulary scene graph generation with prompt-based finetuning,

    T. He, L. Gao, J. Song, and Y .-F. Li, “Towards open-vocabulary scene graph generation with prompt-based finetuning,” inEuropean Conference on Computer Vision. Springer, 2022, pp. 56–73

    2022

  40. [40]

    Learning to generate scene graph from natural language supervision. in 2021 ieee,

    Y . Zhong, J. Shi, J. Yang, C. Xu, and Y . Li, “Learning to generate scene graph from natural language supervision. in 2021 ieee,” inCVF International Conference on Computer Vision (ICCV), 2021, pp. 1803– 1814

    2021

  41. [41]

    Unbiased scene graph generation from biased training,

    K. Tang, Y . Niu, J. Huang, J. Shi, and H. Zhang, “Unbiased scene graph generation from biased training,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 3716– 3725

    2020

  42. [42]

    Visual genome: Connecting language and vision using crowdsourced dense image annotations,

    R. Krishna, Y . Zhu, O. Groth, J. Johnson, K. Hata, J. Kravitz, S. Chen, Y . Kalantidis, L.-J. Li, D. A. Shammaet al., “Visual genome: Connecting language and vision using crowdsourced dense image annotations,” International journal of computer vision, vol. 123, pp. 32–73, 2017

    2017

  43. [43]

    Gaussian Error Linear Units (GELUs)

    D. Hendrycks and K. Gimpel, “Gaussian error linear units (gelus),”arXiv preprint arXiv:1606.08415, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  44. [44]

    Generating semantically precise scene graphs from textual descriptions for improved image retrieval,

    S. Schuster, R. Krishna, A. Chang, L. Fei-Fei, and C. D. Manning, “Generating semantically precise scene graphs from textual descriptions for improved image retrieval,” inProceedings of the fourth workshop on vision and language, 2015, pp. 70–80

    2015

  45. [45]

    Open-vocabulary detr with conditional matching,

    Y . Zang, W. Li, K. Zhou, C. Huang, and C. C. Loy, “Open-vocabulary detr with conditional matching,” inEuropean Conference on Computer Vision. Springer, 2022, pp. 106–122

    2022

  46. [46]

    Promptdet: Towards open-vocabulary detection using uncurated images,

    C. Feng, Y . Zhong, Z. Jie, X. Chu, H. Ren, X. Wei, W. Xie, and L. Ma, “Promptdet: Towards open-vocabulary detection using uncurated images,” inEuropean Conference on Computer Vision. Springer, 2022, pp. 701–717

    2022

  47. [47]

    Dis- tilling detr with visual-linguistic knowledge for open-vocabulary object detection,

    L. Li, J. Miao, D. Shi, W. Tan, Y . Ren, Y . Yang, and S. Pu, “Dis- tilling detr with visual-linguistic knowledge for open-vocabulary object detection,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 6501–6510

    2023

  48. [48]

    Open-vocabulary object detection using captions,

    A. Zareian, K. D. Rosa, D. H. Hu, and S.-F. Chang, “Open-vocabulary object detection using captions,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14 393–14 402

    2021

  49. [49]

    Proxydet: Synthe- sizing proxy novel classes via classwise mixup for open-vocabulary object detection,

    J. Jeong, G. Park, J. Yoo, H. Jung, and H. Kim, “Proxydet: Synthe- sizing proxy novel classes via classwise mixup for open-vocabulary object detection,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 3, 2024, pp. 2462–2470

    2024

  50. [50]

    Retrieval-augmented open- vocabulary object detection,

    J. Kim, E. Cho, S. Kim, and H. J. Kim, “Retrieval-augmented open- vocabulary object detection,” inProceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, 2024, pp. 17 427– 17 436

    2024

  51. [51]

    Benefit from seen: Enhancing open- vocabulary object detection by bridging visual and textual co-occurrence knowledge,

    Y . Li, J. Niu, and T. Ren, “Benefit from seen: Enhancing open- vocabulary object detection by bridging visual and textual co-occurrence knowledge,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2025, pp. 22 110–22 119

    2025

  52. [52]

    Regionclip: Region-based language-image pretraining,

    Y . Zhong, J. Yang, P. Zhang, C. Li, N. Codella, L. H. Li, L. Zhou, X. Dai, L. Yuan, Y . Liet al., “Regionclip: Region-based language-image pretraining,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16 793–16 803

    2022

  53. [53]

    Learning to prompt for open-vocabulary object detection with vision-language model,

    Y . Du, F. Wei, Z. Zhang, M. Shi, Y . Gao, and G. Li, “Learning to prompt for open-vocabulary object detection with vision-language model,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14 084–14 093

    2022

  54. [54]

    Exploring multi-modal con- textual knowledge for open-vocabulary object detection,

    Y . Xu, M. Zhang, X. Yang, and C. Xu, “Exploring multi-modal con- textual knowledge for open-vocabulary object detection,”IEEE Trans- actions on Image Processing, 2024

    2024

  55. [55]

    F-vlm: Open-vocabulary object detection upon frozen vision and language models.arXiv preprint arXiv:2209.15639, 2022

    W. Kuo, Y . Cui, X. Gu, A. Piergiovanni, and A. Angelova, “F-vlm: Open-vocabulary object detection upon frozen vision and language models,”arXiv preprint arXiv:2209.15639, 2022

    work page arXiv 2022

  56. [56]

    Microsoft coco: Common objects in context,

    T.-Y . Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll ´ar, and C. L. Zitnick, “Microsoft coco: Common objects in context,” inComputer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 2014, pp. 740–755

    2014

  57. [57]

    Lvis: A dataset for large vocabulary instance segmentation,

    A. Gupta, P. Dollar, and R. Girshick, “Lvis: A dataset for large vocabulary instance segmentation,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 5356– 5364

    2019

  58. [58]

    Microsoft COCO Captions: Data Collection and Evaluation Server

    X. Chen, H. Fang, T.-Y . Lin, R. Vedantam, S. Gupta, P. Doll ´ar, and C. L. Zitnick, “Microsoft coco captions: Data collection and evaluation server,”arXiv preprint arXiv:1504.00325, 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  59. [59]

    Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image cap- tioning,

    P. Sharma, N. Ding, S. Goodman, and R. Soricut, “Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image cap- tioning,” inProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018, pp. 2556– 2565

    2018

  60. [60]

    Pytorch: An imperative style, high-performance deep learning library,

    A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antigaet al., “Pytorch: An imperative style, high-performance deep learning library,”Advances in neural information processing systems, vol. 32, 2019

    2019

  61. [61]

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

    A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gellyet al., “An image is worth 16x16 words: Transformers for image recognition at scale,”arXiv preprint arXiv:2010.11929, 2020

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  62. [62]

    Feature pyramid networks for object detection,

    T.-Y . Lin, P. Doll´ar, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2117–2125

    2017

  63. [63]

    Aligning pretraining for detection via object-level contrastive learning,

    F. Wei, Y . Gao, Z. Wu, H. Hu, and S. Lin, “Aligning pretraining for detection via object-level contrastive learning,”Advances in Neural Information Processing Systems, vol. 34, pp. 22 682–22 694, 2021

    2021

  64. [64]

    Objects365: A large-scale, high-quality dataset for object detection,

    S. Shao, Z. Li, T. Zhang, C. Peng, G. Yu, X. Zhang, J. Li, and J. Sun, “Objects365: A large-scale, high-quality dataset for object detection,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 8430–8439

    2019

  65. [65]

    Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks,

    A. Chattopadhay, A. Sarkar, P. Howlader, and V . N. Balasubramanian, “Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks,” in2018 IEEE winter conference on applica- tions of computer vision (WACV). IEEE, 2018, pp. 839–847

    2018