{"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/2408-01120","title":"An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding","arxiv_id":"2408.01120","date":"2024-08-02","proceeding":null,"authors":["Wei Chen","Long Chen","Yu Wu"],"abstract":"Most advanced visual grounding methods rely on Transformers for visual-linguistic feature fusion. However, these Transformer-based approaches encounter a significant drawback: the computational costs escalate quadratically due to the self-attention mechanism in the Transformer Encoder, particularly when dealing with high-resolution images or long context sentences. This quadratic increase in computational burden restricts the applicability of visual grounding to more intricate scenes, such as conversation-based reasoning segmentation, which involves lengthy language expressions. In this paper, we propose an efficient and effective multi-task visual grounding (EEVG) framework based on Transformer Decoder to address this issue, which reduces the cost in both language and visual aspects. In the language aspect, we employ the Transformer Decoder to fuse visual and linguistic features, where linguistic features are input as memory and visual features as queries. This allows fusion to scale linearly with language expression length. In the visual aspect, we introduce a parameter-free approach to reduce computation by eliminating background visual tokens based on attention scores. We then design a light mask head to directly predict segmentation masks from the remaining sparse feature maps. Extensive results and ablation studies on benchmarks demonstrate the efficiency and effectiveness of our approach. Code is available in https://github.com/chenwei746/EEVG.","url_abs":"https://arxiv.org/abs/2408.01120v1","url_pdf":"https://arxiv.org/pdf/2408.01120v1.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":"2408-01120","repo_url":"https://github.com/chenwei746/eevg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"reasoning-segmentation","task_name":"Reasoning Segmentation"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.01120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01120"}},"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/chenwei746/eevg","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":9,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":15,"ran":11,"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":15,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/SwinT.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/SwinT.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"339a722b24c73c52","entry":"crop","repo":"chenwei746/eevg","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/datasets/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"339a722b24c73c52"}},{"code_sha256_prefix":"f1cc2143d1c43e52","entry":"dice_loss","repo":"chenwei746/eevg","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/utils/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1cc2143d1c43e52"}},{"code_sha256_prefix":"68586bc611262c8b","entry":"get_norm","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/ViTDet.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/ViTDet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"68586bc611262c8b"}},{"code_sha256_prefix":"087ddc306a2edb7a","entry":"resize_according_to_long_side","repo":"chenwei746/eevg","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/datasets/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"087ddc306a2edb7a"}},{"code_sha256_prefix":"974f724a742dfcdf","entry":"resize_according_to_short_side","repo":"chenwei746/eevg","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/datasets/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"974f724a742dfcdf"}},{"code_sha256_prefix":"0ce2b81bef4f1424","entry":"sigmoid_focal_loss","repo":"chenwei746/eevg","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/utils/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ce2b81bef4f1424"}},{"code_sha256_prefix":"750facb8c52e8864","entry":"window_partition","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/ViTDet.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/ViTDet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"750facb8c52e8864"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/SwinT.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/SwinT.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"535942f820542fb9","entry":"window_unpartition","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/ViTDet.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/ViTDet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"535942f820542fb9"}},{"code_sha256_prefix":"4f1cb44ca3cb9f60","entry":"with_pos_embed","repo":"chenwei746/eevg","repo_kind":"official","path":"models/decoder.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f1cb44ca3cb9f60"}},{"code_sha256_prefix":"697f14f5bf508a68","entry":"convert_examples_to_features","repo":"chenwei746/eevg","repo_kind":"official","path":"datasets/data_loader.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/datasets/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"697f14f5bf508a68"}},{"code_sha256_prefix":"9679406ab6ed7eba","entry":"load_checkpoint","repo":"chenwei746/eevg","repo_kind":"official","path":"models/visual_model/SwinT.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/visual_model/SwinT.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9679406ab6ed7eba"}},{"code_sha256_prefix":"17bc17d91de1161a","entry":"multi_head_attention_forward","repo":"chenwei746/eevg","repo_kind":"official","path":"models/decoder_layer/multi_head_attention.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/decoder_layer/multi_head_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"17bc17d91de1161a"}},{"code_sha256_prefix":"e4f50d4eeb6144e9","entry":"read_examples","repo":"chenwei746/eevg","repo_kind":"official","path":"datasets/data_loader.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/datasets/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4f50d4eeb6144e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}