{"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/diffusioninst-diffusion-model-for-instance","title":"DiffusionInst: Diffusion Model for Instance Segmentation","arxiv_id":"2212.02773","date":"2022-12-06","proceeding":null,"authors":["Zhangxuan Gu","Haoxing Chen","Zhuoer Xu","Jun Lan","Changhua Meng","Weiqiang Wang"],"abstract":"Diffusion frameworks have achieved comparable performance with previous state-of-the-art image generation models. Researchers are curious about its variants in discriminative tasks because of its powerful noise-to-image denoising pipeline. This paper proposes DiffusionInst, a novel framework that represents instances as instance-aware filters and formulates instance segmentation as a noise-to-filter denoising process. The model is trained to reverse the noisy groundtruth without any inductive bias from RPN. During inference, it takes a randomly generated filter as input and outputs mask in one-step or multi-step denoising. Extensive experimental results on COCO and LVIS show that DiffusionInst achieves competitive performance compared to existing instance segmentation models with various backbones, such as ResNet and Swin Transformers. We hope our work could serve as a strong baseline, which could inspire designing more efficient diffusion frameworks for challenging discriminative tasks. Our code is available in https://github.com/chenhaoxing/DiffusionInst.","url_abs":"https://arxiv.org/abs/2212.02773v3","url_pdf":"https://arxiv.org/pdf/2212.02773v3.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":"diffusioninst-diffusion-model-for-instance","repo_url":"https://github.com/chenhaoxing/DiffusionInst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"diffusioninst-diffusion-model-for-instance","repo_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"model","task_name":"model"}],"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":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"DiffusionInst-SwinL","rank_in_archive_order":30,"of":112,"metrics":{"mask AP":"48.3"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"DiffusionInst-SwinB","rank_in_archive_order":32,"of":112,"metrics":{"mask AP":"47.6"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"DiffusionInst-ResNet101","rank_in_archive_order":61,"of":112,"metrics":{"mask AP":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"DiffusionInst-ResNet50","rank_in_archive_order":94,"of":112,"metrics":{"mask AP":"37.1"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"DiffusionInst-SwinL","rank_in_archive_order":9,"of":25,"metrics":{"mask AP":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"DiffusionInst-SwinB","rank_in_archive_order":12,"of":25,"metrics":{"mask AP":"36"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"DiffusionInst-ResNet101","rank_in_archive_order":22,"of":25,"metrics":{"mask AP":"27"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"DiffusionInst-ResNet50","rank_in_archive_order":25,"of":25,"metrics":{"mask AP":"22.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02773"}},"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/alipay/diffusion-model-for-instance-segmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenhaoxing/DiffusionInst","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":5,"ran_honours":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"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":0,"samples":[{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/detector.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/detector.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"aa6da43d05cfaf65","entry":"all_gather","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/misc.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/misc.py","link_basis":"harvester_set","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":"aa6da43d05cfaf65"}},{"code_sha256_prefix":"e0a06ded5d4f6c3c","entry":"box_cxcywh_to_xyxy","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/box_ops.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0a06ded5d4f6c3c"}},{"code_sha256_prefix":"ce749f837424dd8c","entry":"box_iou","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/box_ops.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce749f837424dd8c"}},{"code_sha256_prefix":"031b02fb990284ba","entry":"box_xyxy_to_cxcywh","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/box_ops.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"031b02fb990284ba"}},{"code_sha256_prefix":"3f82133185c8bcb4","entry":"collate_fn","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/misc.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/misc.py","link_basis":"harvester_set","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":"3f82133185c8bcb4"}},{"code_sha256_prefix":"8e8107f647130237","entry":"colormap","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/colormap.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/colormap.py","link_basis":"harvester_set","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":"8e8107f647130237"}},{"code_sha256_prefix":"d5c3a7cf666001a1","entry":"get_model_ema_state","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/model_ema.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/model_ema.py","link_basis":"harvester_set","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":"d5c3a7cf666001a1"}},{"code_sha256_prefix":"05992505df9ef0cd","entry":"reduce_dict","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/misc.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/misc.py","link_basis":"harvester_set","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":"05992505df9ef0cd"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/swintransformer.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/swintransformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/swintransformer.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/swintransformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"4c1065395ab68be4","entry":"apply_model_ema","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/model_ema.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/model_ema.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":"4c1065395ab68be4"}},{"code_sha256_prefix":"250948d3a9b051a5","entry":"dice_coefficient","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/loss.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/loss.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":"250948d3a9b051a5"}},{"code_sha256_prefix":"1e00541b5a150708","entry":"may_get_ema_checkpointer","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/util/model_ema.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/util/model_ema.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":"1e00541b5a150708"}},{"code_sha256_prefix":"0aa3aa3d68d26355","entry":"parse_dynamic_params","repo":"alipay/diffusion-model-for-instance-segmentation","repo_kind":"listed","path":"diffusioninst/loss.py","file_url":"https://github.com/alipay/diffusion-model-for-instance-segmentation/blob/HEAD/diffusioninst/loss.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":"0aa3aa3d68d26355"}},{"code_sha256_prefix":"fe699ae8220daf07","entry":"plot_precision_recall","repo":"chenhaoxing/DiffusionInst","repo_kind":"official","path":"diffusioninst/util/plot_utils.py","file_url":"https://github.com/chenhaoxing/DiffusionInst/blob/HEAD/diffusioninst/util/plot_utils.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":"fe699ae8220daf07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}