{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/self-attention-message-passing-for","title":"Self-Attention Message Passing for Contrastive Few-Shot Learning","arxiv_id":"2210.06339","date":"2022-10-12","proceeding":null,"authors":["Ojas Kishorkumar Shirekar","Anuj Singh","Hadi Jamali-Rad"],"abstract":"Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level. Unsupervised few-shot learning (U-FSL) is the pursuit of bridging this gap between machines and humans. Inspired by the capacity of graph neural networks (GNNs) in discovering complex inter-sample relationships, we propose a novel self-attention based message passing contrastive learning approach (coined as SAMP-CLR) for U-FSL pre-training. We also propose an optimal transport (OT) based fine-tuning strategy (we call OpT-Tune) to efficiently induce task awareness into our novel end-to-end unsupervised few-shot classification framework (SAMPTransfer). Our extensive experimental results corroborate the efficacy of SAMPTransfer in a variety of downstream few-shot classification scenarios, setting a new state-of-the-art for U-FSL on both miniImagenet and tieredImagenet benchmarks, offering up to 7%+ and 5%+ improvements, respectively. Our further investigations also confirm that SAMPTransfer remains on-par with some supervised baselines on miniImagenet and outperforms all existing U-FSL baselines in a challenging cross-domain scenario. Our code can be found in our GitHub repository at https://github.com/ojss/SAMPTransfer/.","url_abs":"https://arxiv.org/abs/2210.06339v1","url_pdf":"https://arxiv.org/pdf/2210.06339v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"self-attention-message-passing-for","repo_url":"https://github.com/ojss/samptransfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"unsupervised-few-shot-image-classification","task_name":"Unsupervised Few-Shot Image Classification"},{"task_slug":"unsupervised-few-shot-learning","task_name":"Unsupervised Few-Shot Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"graph-self-attention","method_name":"Graph Self-Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"SAMPTransfer (Conv4)","rank_in_archive_order":5,"of":28,"metrics":{"Accuracy":"61.02"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-1","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"SAMPTransfer (Conv4)","rank_in_archive_order":10,"of":28,"metrics":{"Accuracy":"72.52"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-2","task":"Unsupervised Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"SAMPTransfer (Conv4)","rank_in_archive_order":8,"of":12,"metrics":{"Accuracy":"49.10"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-3","task":"Unsupervised Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"SAMPTransfer (Conv4)","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"65.19"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.06339","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}