Elamur Research
☰
home / papers / 2023 / ImageBind: One Embedding Space To Bind Them All

ImageBind: One Embedding Space To Bind Them All

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "arXiv — non-exclusive license to distribute" does not allow redistributing the text itself. Original — arxiv.org/pdf/2305.05665

Summary

ImageBind addresses a practical obstacle to building one representation space for many sensory modalities: no large dataset records all modalities together. The authors observe that images co-occur naturally with many other signals. They use the image as a shared anchor and connect six modalities: images/video, text, audio, depth, thermal and IMU. Each non-image encoder, a Transformer (ViT-style), is trained with a symmetric InfoNCE contrastive loss. This loss pulls it toward the image embedding of its paired sample, using web image–text pairs, video–audio clips, image–depth and image–thermal captures, and egocentric video with IMU. The image and text side can start from a pretrained CLIP model. Because every modality is tied to images, modalities never seen together, such as audio and text, also end up aligned. This enables zero-shot classification and retrieval without direct pairs. The resulting space supports cross-modal retrieval, embedding arithmetic, and plugging audio into Detic or DALLE-2. It reaches state-of-the-art emergent zero-shot results, competitive with audio-text-supervised specialists. This matters because cheap, naturally paired data can substitute for costly all-modality corpora.

Key points

  • The method needs only image-paired data. It does not need every combination of modality pairs, yet it achieves emergent alignment between pairs such as (audio, text) and (depth, text) without training on them.
  • Emergent zero-shot audio results match or beat models trained with explicit audio–text supervision on ESC, Clotho and AudioCaps. ImageBind also performs strongly in few-shot settings.
  • Ablations favour several design choices:
    • a fixed temperature over a learnable one;
    • a linear projection head over an MLP;
    • spatially aligned image–depth crops and temporally aligned audio–video;
    • longer training.
    • Larger audio encoders help, while smaller depth encoders help on the small depth data.
  • The best batch size depends on the modality. NYU-D peaks at 512 (47.3), and ESC peaks at 2k (56.7).
  • ImageBind can serve as a tool for evaluating vision models. With a frozen DINO image encoder, ESC accuracy is 44.7, against 25.0 with a frozen DeiT. This holds even though DeiT scores higher on ImageNet-1K (74.4 vs 64.4).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Other

Cited by

111 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 106 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2305.05665 · arXiv 2305.05665

@misc{girdhar2023imagebind,
  title = {{ImageBind: One Embedding Space To Bind Them All}},
  author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan},
  year = {2023},
  doi = {10.48550/arxiv.2305.05665},
  eprint = {2305.05665},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.05665}
}

References

88 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katie Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob Menick, Sebastian Borgeaud, Andrew Brock… find our card
  2. Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovic, Jason Ramapuram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. Self-supervised multimodal versatile networks. NeurIPS, 2020. 2 find
  3. Relja Arandjelovic and Andrew Zisserman. Look, listen and learn. In ICCV, 2017. 1, 2 find
  4. Roman Bachmann, David Mizrahi, Andrei Atanov, and Amir Zamir. MultiMAE: Multi-modal Multi-task Masked Autoencoders. In ECCV, 2022. 1, 6 find
  5. Max Bain, Arsha Nagrani, Gül Varol, and Andrew Zisserman. Frozen in time: A joint video and image encoder for end-to-end retrieval. In ICCV, 2021. 5 find
  6. Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. Emerging properties in self-supervised vision transformers. In ICCV, 2021. 8 find our card
  7. João Carreira and Andrew Zisserman. Quo vadis, action recognition? A new model and the kinetics dataset. In CVPR, 2017. 3 find
  8. Honglie Chen, Weidi Xie, Andrea Vedaldi, and Andrew Zisserman. Vggsound: A large-scale audio-visual dataset. In ICASSP, 2020. 4, 12 find
  9. Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, and Shlomo Dubnov. Hts-at: A hierarchical token-semantic audio transformer for sound classification and detection. In ICASSP, 2022. 5 find
  10. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. In ICML, 2020. 7, 14 find our card
  11. Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, and Jenia Jitsev. Reproducible scaling laws for contrastive language-image learning. In CVPR, 2023. 4 find
  12. Ekin D Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V Le. Randaugment: Practical automated data augmentation with a reduced search space. In CVPR, 2020. 7 find
  13. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2021. 3 find
  14. Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. VSE++: Improving Visual-Semantic Embeddings with Hard Negatives. In BMVC, 2018. 2 find
  15. Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097, 2021. 2 — [arXiv:2106.11097](https://arxiv.org/abs/2106.11097) find
  16. Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, and Kaiming He. Masked autoencoders as spatiotemporal learners. In NeurIPS, 2022. 13 find
  17. Frederic Font, Gerard Roma, and Xavier Serra. Freesound technical demo. In ACM MM, 2013. 4, 12 find
  18. Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc’Aurelio Ranzato, and Tomas Mikolov. Devise: A deep visual-semantic embedding model. NeurIPS, 2013. 2 find
  19. Jort F. Gemmeke, Daniel P. W. Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R. Channing Moore, Manoj Plakal, and Marvin Ritter. Audio set: An ontology and human-labeled dataset for audio events. In ICASSP, 2017. 4, 12 find
  20. Rohit Girdhar, Alaaeldin El-Nouby, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, and Ishan Misra. OmniMAE: Single Model Masked Pretraining on Images and Videos. In CVPR, 2023. 2, 3 find
  21. Rohit Girdhar, Mannat Singh, Nikhila Ravi, Laurens van der Maaten, Armand Joulin, and Ishan Misra. Omnivore: A Single Model for Many Visual Modalities. In CVPR, 2022. 2, 4, 5, 12 find
  22. Yuan Gong, Yu-An Chung, and James Glass. AST: Audio Spectrogram Transformer. In Interspeech, 2021. 3, 4, 13 find
  23. Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong X… find
  24. Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. Open-vocabulary object detection via vision and language knowledge distillation. In ICLR, 2022. 2 find
  25. Saurabh Gupta, Pablo Arbelaez, and Jitendra Malik. Perceptual organization and recognition of indoor scenes from rgb-d images. In CVPR, 2013. 13 find
  26. Saurabh Gupta, Ross Girshick, Pablo Arbeláez, and Jitendra Malik. Learning rich features from rgb-d images for object detection and segmentation. In ECCV, 2014. 13 find
  27. Andrey Guzhov, Federico Raue, Jörn Hees, and Andreas Dengel. AudioCLIP: Extending CLIP to Image, Text and Audio. arXiv preprint arXiv:2106.13043, 2021. 2, 3, 4, 5 — [arXiv:2106.13043](https://arxiv.org/abs/2106.13043) find
  28. Raia Hadsell, Sumit Chopra, and Yann LeCun. Dimensionality reduction by learning an invariant mapping. In CVPR, 2006. 3 find
  29. Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, and Kilian Q Weinberger. Deep networks with stochastic depth. In ECCV, 2016. 14 find
  30. Gabriel Ilharco, Mitchell Wortsman, Ross Wightman, Cade Gordon, Nicholas Carlini, Rohan Taori, Achal Dave, Vaishaal Shankar, Hongseok Namkoong, John Miller, Hannaneh Hajishirzi, Ali Farhadi, and Ludwig Schmidt. Openclip, 2021. 4, 5 find
  31. Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. Scaling up visual and vision-language representation learning with noisy text supervision. In ICML, 2021. 1, 2 find our card
  32. Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, and Wenli Zhou. Llvip: A visible-infrared paired dataset for low-light vision. In ICCV, 2021. 4, 12, 13 find
  33. Melvin Johnson, Mike Schuster, Quoc V Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, and Jeffrey Dean. Google’s multilingual neural machine translation system: Enabling zero-shot translation. In ACL, 2017. 2 find
  34. Armand Joulin, Laurens van der Maaten, Allan Jabri, and Nicolas Vasilache. Learning visual features from large weakly supervised data. In ECCV, 2016. 2 find
  35. Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, Mustafa Suleyman, and Andrew Zisserman. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950, 2017. 4 — [arXiv:1705.06950](https://arxiv.org/abs/1705.06950) find
  36. Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, and Dima Damen. Slow-fast auditory streams for audio recognition. In ICASSP, 2021. 5 find
  37. Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. Audiocaps: Generating captions for audios in the wild. In NAACL, 2019. 4, 12 find
  38. Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. Unifying visual-semantic embeddings with multimodal neural language models. In NeurIPS Workshop, 2014. 2 find our card
  39. Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, and Gerhard Widmer. Efficient training of audio transformers with patchout. In Interspeech, 2022. 5 find
  40. Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. Unsupervised machine translation using monolingual corpora only. In ICLR, 2018. 2 find our card
  41. Boyi Li, Kilian Q Weinberger, Serge Belongie, Vladlen Koltun, and René Ranftl. Language-driven semantic segmentation. In ICLR, 2022. 2 find
  42. Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, and Mostafa Dehghani. Polyvit: Co-training vision transformers on images, videos and audio. arXiv preprint arXiv:2111.12993, 2021. 2 — [arXiv:2111.12993](https://arxiv.org/abs/2111.12993) find
  43. Ziyi Lin, Shijie Geng, Renrui Zhang, Peng Gao, Gerard de Melo, Xiaogang Wang, Jifeng Dai, Yu Qiao, and Hongsheng Li. Frozen clip models are efficient video learners. In ECCV, 2022. 2 find
  44. Xingbin Liu, Jinghao Zhou, Tao Kong, Xianming Lin, and Rongrong Ji. Exploring target representations for masked autoencoders. arXiv preprint arXiv:2209.03917, 2022. 2 — [arXiv:2209.03917](https://arxiv.org/abs/2209.03917) find
  45. Huaishao Luo, Lei Ji, Ming Zhong, Yang Chen, Wen Lei, Nan Duan, and Tianrui Li. CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. arXiv preprint arXiv:2104.08860, 2021. 2 — [arXiv:2104.08860](https://arxiv.org/abs/2104.08860) find
  46. Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, and Laurens Van Der Maaten. Exploring the limits of weakly supervised pretraining. In ECCV, 2018. 1 find
  47. Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev, Josef Sivic, and Andrew Zisserman. End-to-end learning of visual representations from uncurated instructional videos. In CVPR, 2020. 2 find
  48. Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, and Josef Sivic. Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. ICCV, 2019. 2 find
  49. Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, and Josef Sivic. Howto100m: Learning a text-video embedding by watching hundred million narrated video clips. In ICCV, 2019. 5 find
  50. Pedro Morgado, Nuno Vasconcelos, and Ishan Misra. Audio-visual instance discrimination with cross-modal agreement. In CVPR, 2021. 1, 2, 3, 5 find
  51. Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold, Anja Hauth, Santiago Manen, Chen Sun, and Cordelia Schmid. Learning audio-video modalities from image captions. In ECCV, 2022. 2, 4, 5 find
  52. Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, and Chen Sun. Attention bottlenecks for multimodal fusion. In NeurIPS, 2021. 5 find
  53. Andreea-Maria Oncescu, A Koepke, Joao F Henriques, Zeynep Akata, and Samuel Albanie. Audio retrieval with natural language queries. In Interspeech, 2021. 5, 12 find
  54. Aaron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. In NeurIPS, 2018. 3 find our card
  55. Andrew Owens and Alexei A Efros. Audio-visual scene analysis with self-supervised multisensory features. In ECCV, 2018. 1 find
  56. Mandela Patrick, Yuki M Asano, Ruth Fong, João F Henriques, Geoffrey Zweig, and Andrea Vedaldi. Multi-modal self-supervision from generalized data transformations. In ICCV, 2021. 1 find
  57. Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander Hauptmann, Joao Henriques, and Andrea Vedaldi. Support-set bottlenecks for video-text representation learning. In ICLR, 2021. 5 find
  58. Zhiliang Peng, Li Dong, Hangbo Bao, Qixiang Ye, and Furu Wei. BEiT v2: Masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366, 2022. 2 — [arXiv:2208.06366](https://arxiv.org/abs/2208.06366) find
  59. Karol J Piczak. Esc: Dataset for environmental sound classification. In ACM MM, 2015. 4, 12 find
  60. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In ICML, 2021. 1, 2, 3, 4, 5, 7, 13, 14, 15 find our card
  61. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022. 1, 6, 13 find our card
  62. René Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. TPAMI, 2020. 13 find
  63. Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015. 4 find our card
  64. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. LAION-5B: An open large-scal… find our card
  65. Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. In NeurIPS Workshop, 2021. 1 find our card
  66. Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, 2012. 4, 12, 13 find
  67. Mannat Singh, Laura Gustafson, Aaron Adcock, Vinicius de Freitas Reis, Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Dollár, and Laurens van der Maaten. Revisiting weakly supervised pre-training of visual perception models. In CVPR, 2022. 5 find
  68. Richard Socher, Andrej Karpathy, Quoc V Le, Christopher D Manning, and Andrew Y Ng. Grounded compositional semantics for finding and describing images with sentences. ACL, 2014. 2 find our card
  69. Shuran Song, Samuel P Lichtenberg, and Jianxiong Xiao. Sun rgb-d: A rgb-d scene understanding benchmark suite. In CVPR, 2015. 4, 12 find
  70. Yonglong Tian, Dilip Krishnan, and Phillip Isola. Contrastive multiview coding. arXiv preprint arXiv:1906.05849, 2019. 1, 2, 3, 7 — [arXiv:1906.05849](https://arxiv.org/abs/1906.05849) find
  71. Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In NeurIPS, 2022. 13 find
  72. Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou. Training data-efficient image transformers & distillation through attention. In ICML, 2021. 8 find our card
  73. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, 2017. 3 find
  74. Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Yu-Gang Jiang, Luowei Zhou, and Lu Yuan. BEVT: Bert pretraining of video transformers. In CVPR, 2022. 2 find
  75. Yixuan Wei, Han Hu, Zhenda Xie, Zheng Zhang, Yue Cao, Jianmin Bao, Dong Chen, and Baining Guo. Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141, 2022. 2 — [arXiv:2205.14141](https://arxiv.org/abs/2205.14141) find
  76. Zhirong Wu, Yuanjun Xiong, Stella X Yu, and Dahua Lin. Unsupervised feature learning via non-parametric instance discrimination. In CVPR, 2018. 3 find
  77. Hu Xu, Juncheng Li, Alexei Baevski, Michael Auli, Wojciech Galuba, Florian Metze, and Christoph Feichtenhofer. Masked autoencoders that listen. In NeurIPS, 2022. 6 find
  78. Jun Xu, Tao Mei, Ting Yao, and Yong Rui. Msr-vtt: A large video description dataset for bridging video and language. In CVPR, 2016. 4 find
  79. Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. In ICLR, 2023. 2, 5 find
  80. Shen Yan, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, and Cordelia Schmid. Multiview transformers for video recognition. In CVPR, 2022. 5 find
  81. Kim Youwang, Kim Ji-Yeon, and Tae-Hyun Oh. Clip-actor: Text-driven recommendation and stylization for animating human meshes. In ECCV, 2022. 2 find
  82. Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. Coca: Contrastive captioners are image-text foundation models. TMLR, 2022. 1, 2, 5 find our card
  83. Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, and Pengchuan Zhang. Florence… — [arXiv:2111.11432](https://arxiv.org/abs/2111.11432) find
  84. Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, and Lucas Beyer. Lit: Zero-shot transfer with locked-image text tuning. In CVPR, 2022. 2 find
  85. Renrui Zhang, Ziyu Guo, Wei Zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, and Hongsheng Li. Pointclip: Point cloud understanding by clip. In CVPR, 2022. 2, 3 find
  86. Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, and Yi Yang. Random erasing data augmentation. In AAAI, 2020. 7 find
  87. Bolei Zhou, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, and Aude Oliva. Learning deep features for scene recognition using places database. In NeurIPS, 2014. 4 find
  88. Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, and Ishan Misra. Detecting twenty-thousand classes using image-level supervision. In ECCV, 2022. 2, 6, 13 A. Datasets and Metrics find