{"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/structured-click-control-in-transformer-based","title":"Structured Click Control in Transformer-based Interactive Segmentation","arxiv_id":"2405.04009","date":"2024-05-07","proceeding":null,"authors":["Long Xu","Yongquan Chen","Rui Huang","Feng Wu","Shiwu Lai"],"abstract":"Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. Then the graph nodes will be aggregated to obtain structured interaction features. Finally, the dual cross-attention will be used to inject structured interaction features into vision Transformer features, thereby enhancing the control of clicks over segmentation results. Extensive experiments demonstrated the proposed algorithm can serve as a general structure in improving Transformer-based interactive segmenta?tion performance. The code and data will be released at https://github.com/hahamyt/scc.","url_abs":"https://arxiv.org/abs/2405.04009v1","url_pdf":"https://arxiv.org/pdf/2405.04009v1.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":"structured-click-control-in-transformer-based","repo_url":"https://github.com/hahamyt/scc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"interactive-segmentation","task_name":"Interactive Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"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=2405.04009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04009"}},"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/hahamyt/scc","reach":null}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"e3da1afeb3144e27","entry":"AdjBlock","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e3da1afeb3144e27"}},{"code_sha256_prefix":"df5cfe9ca081ba57","entry":"CrossAttention","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"df5cfe9ca081ba57"}},{"code_sha256_prefix":"1d174c7f1898b9b2","entry":"GAT","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1d174c7f1898b9b2"}},{"code_sha256_prefix":"6e2dfb3168df266d","entry":"GraphAttentionLayer","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6e2dfb3168df266d"}},{"code_sha256_prefix":"da0250470ea50ce7","entry":"SimBlock","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"da0250470ea50ce7"}},{"code_sha256_prefix":"fe573f7a27b979af","entry":"calculate_binary_cigr","repo":"hahamyt/scc","repo_kind":"official","path":"scripts/evaluate_model.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/scripts/evaluate_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fe573f7a27b979af"}},{"code_sha256_prefix":"fca7b0a20cde7062","entry":"get_predictor_and_zoomin_params","repo":"hahamyt/scc","repo_kind":"official","path":"scripts/evaluate_model.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/scripts/evaluate_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fca7b0a20cde7062"}},{"code_sha256_prefix":"797caf177e62b27e","entry":"mean_query","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"797caf177e62b27e"}},{"code_sha256_prefix":"7af6422c5e3a96fe","entry":"GATFusionBlock","repo":"hahamyt/scc","repo_kind":"official","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7af6422c5e3a96fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}