{"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/adaptive-split-fusion-transformer","title":"Adaptive Split-Fusion Transformer","arxiv_id":"2204.12196","date":"2022-04-26","proceeding":null,"authors":["Zixuan Su","Hao Zhang","Jingjing Chen","Lei Pang","Chong-Wah Ngo","Yu-Gang Jiang"],"abstract":"Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range global connections between localities for holistic learning. Inspired by this complementary nature, there is a growing interest in designing hybrid models to best utilize each technique. Current hybrids merely replace convolutions as simple approximations of linear projection or juxtapose a convolution branch with attention, without concerning the importance of local/global modeling. To tackle this, we propose a new hybrid named Adaptive Split-Fusion Transformer (ASF-former) to treat convolutional and attention branches differently with adaptive weights. Specifically, an ASF-former encoder equally splits feature channels into half to fit dual-path inputs. Then, the outputs of dual-path are fused with weighting scalars calculated from visual cues. We also design the convolutional path compactly for efficiency concerns. Extensive experiments on standard benchmarks, such as ImageNet-1K, CIFAR-10, and CIFAR-100, show that our ASF-former outperforms its CNN, transformer counterparts, and hybrid pilots in terms of accuracy (83.9% on ImageNet-1K), under similar conditions (12.9G MACs/56.7M Params, without large-scale pre-training). The code is available at: https://github.com/szx503045266/ASF-former.","url_abs":"https://arxiv.org/abs/2204.12196v2","url_pdf":"https://arxiv.org/pdf/2204.12196v2.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":"adaptive-split-fusion-transformer","repo_url":"https://github.com/szx503045266/asf-former","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ASF-former-B","rank_in_archive_order":29,"of":265,"metrics":{"Percentage correct":"98.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ASF-former-S","rank_in_archive_order":32,"of":265,"metrics":{"Percentage correct":"98.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10-image","task":"Image Classification","dataset":"CIFAR-10 Image Classification","model":"ASF-former-S","rank_in_archive_order":1,"of":2,"metrics":{"Params":"19.3M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10-image","task":"Image Classification","dataset":"CIFAR-10 Image Classification","model":"ASF-former-B","rank_in_archive_order":2,"of":2,"metrics":{"Params":"56.7M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ASF-former-B","rank_in_archive_order":378,"of":1060,"metrics":{"Number of params":"56.7M","Top 1 Accuracy":"83.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ASF-former-S","rank_in_archive_order":508,"of":1060,"metrics":{"Number of params":"19.3M","Top 1 Accuracy":"82.7%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.12196","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}