{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/uninet-unified-architecture-search-with","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","arxiv_id":"2110.04035","date":"2021-10-08","proceeding":null,"authors":["Jihao Liu","Hongsheng Li","Guanglu Song","Xin Huang","Yu Liu"],"abstract":"Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those operators to design visual network architectures, and can achieve satisfactory performances to some extent. In this paper, we propose to jointly search the optimal combination of convolution, transformer, and MLP for building a series of all-operator network architectures with high performances on visual tasks. We empirically identify that the widely-used strided convolution or pooling based down-sampling modules become the performance bottlenecks when the operators are combined to form a network. To better tackle the global context captured by the transformer and MLP operators, we propose two novel context-aware down-sampling modules, which can better adapt to the global information encoded by transformer and MLP operators. To this end, we jointly search all operators and down-sampling modules in a unified search space. Notably, Our searched network UniNet (Unified Network) outperforms state-of-the-art pure convolution-based architecture, EfficientNet, and pure transformer-based architecture, Swin-Transformer, on multiple public visual benchmarks, ImageNet classification, COCO object detection, and ADE20K semantic segmentation.","url_abs":"https://arxiv.org/abs/2110.04035v1","url_pdf":"https://arxiv.org/pdf/2110.04035v1.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniNet-B5","rank_in_archive_order":250,"of":1060,"metrics":{"GFLOPs":"23.2","Number of params":"73.5M","Top 1 Accuracy":"85.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniNet-B4","rank_in_archive_order":339,"of":1060,"metrics":{"GFLOPs":"9.9","Number of params":"73.5M","Top 1 Accuracy":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniNet-B2","rank_in_archive_order":510,"of":1060,"metrics":{"GFLOPs":"2.4","Number of params":"22.5M","Top 1 Accuracy":"82.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniNet-B1","rank_in_archive_order":703,"of":1060,"metrics":{"GFLOPs":"0.99","Number of params":"14M","Top 1 Accuracy":"80.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniNet-B0","rank_in_archive_order":783,"of":1060,"metrics":{"GFLOPs":"0.56","Number of params":"11.9M","Top 1 Accuracy":"79.1%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04035","atlas_url":"https://app.syntology.ai/?focus=2110.04035","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.04035"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.04035\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.04035"},"call":"get_concepts_for_paper(arxiv_id=\"2110.04035\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"234c027cd15a33b4c5c28f93593e8243a2203cd57389fc2bd5a0bbecb4768f9e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}