{"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/vision-rwkv-efficient-and-scalable-visual","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","arxiv_id":"2403.02308","date":"2024-03-04","proceeding":null,"authors":["Yuchen Duan","Weiyun Wang","Zhe Chen","Xizhou Zhu","Lewei Lu","Tong Lu","Yu Qiao","Hongsheng Li","Jifeng Dai","Wenhai Wang"],"abstract":"Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks. Similar to the Vision Transformer (ViT), our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage lies in its reduced spatial aggregation complexity, which renders it exceptionally adept at processing high-resolution images seamlessly, eliminating the necessity for windowing operations. Our evaluations demonstrate that VRWKV surpasses ViT's performance in image classification and has significantly faster speeds and lower memory usage processing high-resolution inputs. In dense prediction tasks, it outperforms window-based models, maintaining comparable speeds. These results highlight VRWKV's potential as a more efficient alternative for visual perception tasks. Code is released at https://github.com/OpenGVLab/Vision-RWKV.","url_abs":"https://arxiv.org/abs/2403.02308v3","url_pdf":"https://arxiv.org/pdf/2403.02308v3.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":"vision-rwkv-efficient-and-scalable-visual","repo_url":"https://github.com/OpenGVLab/Vision-RWKV","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"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":"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"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.02308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02308"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OpenGVLab/Vision-RWKV","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"unverified":9},"by_repo_kind":{"official":{"samples":19,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"85eb4384e6e00dc3","entry":"attn_flops","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification/get_flops_backbone.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification/get_flops_backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85eb4384e6e00dc3"}},{"code_sha256_prefix":"c345681a7f3952a1","entry":"build_optimizer","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/optimizer.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c345681a7f3952a1"}},{"code_sha256_prefix":"cc198154486fa894","entry":"get_layer_id_for_vrwkv","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/optimizer.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc198154486fa894"}},{"code_sha256_prefix":"62f6742745cb0637","entry":"get_num_layer_for_vit","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"detection/mmcv_custom/layer_decay_optimizer_constructor.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/detection/mmcv_custom/layer_decay_optimizer_constructor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62f6742745cb0637"}},{"code_sha256_prefix":"7e302eeb245b5b47","entry":"get_num_layer_for_vit","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"segmentation/mmcv_custom/layer_decay_optimizer_constructor.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/segmentation/mmcv_custom/layer_decay_optimizer_constructor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e302eeb245b5b47"}},{"code_sha256_prefix":"6cfeb87841e13fbc","entry":"load_ema_checkpoint","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/utils.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cfeb87841e13fbc"}},{"code_sha256_prefix":"4f76ba4ee84cca1f","entry":"param_groups_lrd_vrwkv","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/optimizer.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f76ba4ee84cca1f"}},{"code_sha256_prefix":"a2d0a36f82b566d4","entry":"q_shift","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/models/vrwkv.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/models/vrwkv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d0a36f82b566d4"}},{"code_sha256_prefix":"d14161cfbbe61ae4","entry":"vrwkv6_flops","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification/get_flops_backbone.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification/get_flops_backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d14161cfbbe61ae4"}},{"code_sha256_prefix":"dcf92f15525d8f6d","entry":"vrwkv_flops","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification/get_flops_backbone.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification/get_flops_backbone.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dcf92f15525d8f6d"}},{"code_sha256_prefix":"bb1a26fe42d7075c","entry":"allreduce_hook","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/ddp_hooks.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/ddp_hooks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb1a26fe42d7075c"}},{"code_sha256_prefix":"21bd5be56c8f79d0","entry":"bf16_compress_hook","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/ddp_hooks.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/ddp_hooks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21bd5be56c8f79d0"}},{"code_sha256_prefix":"f8e2a8ed567765db","entry":"build_model","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/models/build.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/models/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8e2a8ed567765db"}},{"code_sha256_prefix":"07e8b4b487c0abb6","entry":"build_scheduler","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/lr_scheduler.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"07e8b4b487c0abb6"}},{"code_sha256_prefix":"78511e137c0af18c","entry":"convert_22k_head_to_1k","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/utils.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78511e137c0af18c"}},{"code_sha256_prefix":"80450600f7f09b0a","entry":"create_logger","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/logger.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80450600f7f09b0a"}},{"code_sha256_prefix":"26bfffb625dfe211","entry":"fp16_compress_hook","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/ddp_hooks.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/ddp_hooks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26bfffb625dfe211"}},{"code_sha256_prefix":"5037b16e3cb5e09d","entry":"get_config","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/config.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5037b16e3cb5e09d"}},{"code_sha256_prefix":"9f63c219db4ba592","entry":"load_checkpoint","repo":"OpenGVLab/Vision-RWKV","repo_kind":"official","path":"classification_internimage/utils.py","file_url":"https://github.com/OpenGVLab/Vision-RWKV/blob/HEAD/classification_internimage/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f63c219db4ba592"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}