{"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/bridge-past-and-future-overcoming-information","title":"Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection","arxiv_id":"2407.11499","date":"2024-07-16","proceeding":null,"authors":["Qijie Mo","Yipeng Gao","Shenghao Fu","Junkai Yan","AnCong Wu","Wei-Shi Zheng"],"abstract":"In incremental object detection, knowledge distillation has been proven to be an effective way to alleviate catastrophic forgetting. However, previous works focused on preserving the knowledge of old models, ignoring that images could simultaneously contain categories from past, present, and future stages. The co-occurrence of objects makes the optimization objectives inconsistent across different stages since the definition for foreground objects differs across various stages, which limits the model's performance greatly. To overcome this problem, we propose a method called ``Bridge Past and Future'' (BPF), which aligns models across stages, ensuring consistent optimization directions. In addition, we propose a novel Distillation with Future (DwF) loss, fully leveraging the background probability to mitigate the forgetting of old classes while ensuring a high level of adaptability in learning new classes. Extensive experiments are conducted on both Pascal VOC and MS COCO benchmarks. Without memory, BPF outperforms current state-of-the-art methods under various settings. The code is available at https://github.com/iSEE-Laboratory/BPF.","url_abs":"https://arxiv.org/abs/2407.11499v1","url_pdf":"https://arxiv.org/pdf/2407.11499v1.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":"bridge-past-and-future-overcoming-information","repo_url":"https://github.com/isee-laboratory/bpf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11499","atlas_url":"https://app.syntology.ai/?focus=2407.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11499"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/isee-laboratory/bpf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/iSEE-Laboratory/BPF","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"ed0338a30ec1e616","entry":"add_attention_scores","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/modeling/attention_map.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/modeling/attention_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed0338a30ec1e616"}},{"code_sha256_prefix":"374fba1d23321a7b","entry":"calculate_attention_scores_per_img_roi_align","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/modeling/attention_map.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/modeling/attention_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"374fba1d23321a7b"}},{"code_sha256_prefix":"5bb42fad3fc38eff","entry":"next_free_port","repo":"isee-laboratory/bpf","repo_kind":"official","path":"get_free_port.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/get_free_port.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bb42fad3fc38eff"}},{"code_sha256_prefix":"e261fa29066b37e5","entry":"smooth_l1_loss","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/layers/smooth_l1_loss.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/layers/smooth_l1_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e261fa29066b37e5"}},{"code_sha256_prefix":"0c50b7e70bf34d44","entry":"calculate_roi_scores_distillation_losses_new_raw","repo":"iSEE-Laboratory/BPF","repo_kind":"official","path":"maskrcnn_benchmark/distillation/finetune_distillation_all.py","file_url":"https://github.com/iSEE-Laboratory/BPF/blob/HEAD/maskrcnn_benchmark/distillation/finetune_distillation_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c50b7e70bf34d44"}},{"code_sha256_prefix":"06d865291a39b351","entry":"calculate_roi_scores_distillation_losses_old_raw","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/distillation/finetune_distillation_all.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/distillation/finetune_distillation_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06d865291a39b351"}},{"code_sha256_prefix":"910bc10f3fec4d5d","entry":"generate_attention_map","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/modeling/attention_map.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/modeling/attention_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"910bc10f3fec4d5d"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/layers/misc.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/layers/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2902bf4410253ff7"}},{"code_sha256_prefix":"426fd02a2beaf826","entry":"sigmoid_focal_loss_cpu","repo":"isee-laboratory/bpf","repo_kind":"official","path":"maskrcnn_benchmark/layers/sigmoid_focal_loss.py","file_url":"https://github.com/isee-laboratory/bpf/blob/HEAD/maskrcnn_benchmark/layers/sigmoid_focal_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"426fd02a2beaf826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}