{"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/memory-replay-with-data-compression-for-1","title":"Memory Replay with Data Compression for Continual Learning","arxiv_id":"2202.06592","date":"2022-02-14","proceeding":"ICLR 2022 4","authors":["Liyuan Wang","Xingxing Zhang","Kuo Yang","Longhui Yu","Chongxuan Li","Lanqing Hong","Shifeng Zhang","Zhenguo Li","Yi Zhong","Jun Zhu"],"abstract":"Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is mainly built on a small memory buffer containing a few original data, which cannot fully characterize the old data distribution. In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer. Observing that the trade-off between the quality and quantity of compressed data is highly nontrivial for the efficacy of memory replay, we propose a novel method based on determinantal point processes (DPPs) to efficiently determine an appropriate compression quality for currently-arrived training samples. In this way, using a naive data compression algorithm with a properly selected quality can largely boost recent strong baselines by saving more compressed data in a limited storage space. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.","url_abs":"https://arxiv.org/abs/2202.06592v2","url_pdf":"https://arxiv.org/pdf/2202.06592v2.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":"memory-replay-with-data-compression-for-1","repo_url":"https://github.com/lywang3081/MRDC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"data-compression","task_name":"Data Compression"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"point-processes","task_name":"Point Processes"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.06592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06592"}},"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/lywang3081/MRDC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"lywang3081/MRDC","repo_kind":"official","path":"2_LUCIR_+DC/modified_resnet.py","file_url":"https://github.com/lywang3081/MRDC/blob/HEAD/2_LUCIR_%2BDC/modified_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"d34426031c82e5a3","entry":"get_JPEG_img","repo":"lywang3081/MRDC","repo_kind":"official","path":"1_Data_Compression/skimage_save_jpeg.py","file_url":"https://github.com/lywang3081/MRDC/blob/HEAD/1_Data_Compression/skimage_save_jpeg.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":"d34426031c82e5a3"}},{"code_sha256_prefix":"26ada2c605d5580a","entry":"resnet18","repo":"lywang3081/MRDC","repo_kind":"official","path":"2_LUCIR_+DC/resnet.py","file_url":"https://github.com/lywang3081/MRDC/blob/HEAD/2_LUCIR_%2BDC/resnet.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":"26ada2c605d5580a"}},{"code_sha256_prefix":"3d30358a9af495ff","entry":"resnet34","repo":"lywang3081/MRDC","repo_kind":"official","path":"2_LUCIR_+DC/resnet.py","file_url":"https://github.com/lywang3081/MRDC/blob/HEAD/2_LUCIR_%2BDC/resnet.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":"3d30358a9af495ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}