{"url":"/method/dla","slug":"dla","name":"DLA","full_name":"Deep Layer Aggregation","full_name_withheld":false,"description_markdown":"**DLA**, or **Deep Layer Aggregation**,  iteratively and hierarchically merges the feature hierarchy across layers in neural networks to make networks with better accuracy and fewer parameters. \r\n\r\nIn iterative deep aggregation (IDA), aggregation begins at the shallowest, smallest scale and then iteratively merges deeper,\r\nlarger scales. In this way shallow features are refined as\r\nthey are propagated through different stages of aggregation.\r\n\r\nIn hierarchical deep aggregation (HDA), blocks and stages\r\nin a tree are merged to preserve and combine feature channels. With\r\nHDA shallower and deeper layers are combined to learn\r\nricher combinations that span more of the feature hierarchy.\r\nWhile IDA effectively combines stages, it is insufficient\r\nfor fusing the many blocks of a network, as it is still only\r\nsequential.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1707.06484v3","title":"Deep Layer Aggregation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Extractors","url":"/methods/category/feature-extractors","pwc_aliases":[]}],"n_papers_tagged":94,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/linea-fast-and-accurate-line-detection-using","title":"LINEA: Fast and Accurate Line Detection Using Scalable Transformers","date":"2025-05-22","arxiv_id":"2505.16264","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-adversarial","title":"Evaluating the Robustness of Adversarial Defenses in Malware Detection Systems","date":"2025-05-14","arxiv_id":"2505.09342","n_code_links":1,"syntology":null},{"paper":null,"title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court","date":"2025-05-13","arxiv_id":"2505.08439","n_code_links":0,"syntology":null},{"paper":"/paper/sfdla-source-free-document-layout-analysis","title":"SFDLA: Source-Free Document Layout Analysis","date":"2025-03-24","arxiv_id":"2503.18742","n_code_links":1,"syntology":null},{"paper":null,"title":"Modelowanie nieliniowej charakterystyki szerokopasmowych wzmacniaczy radiowych o zmiennym napięciu zasilania; Modeling Nonlinear Characteristics of Wideband Radio Frequency Amplifiers with Variable Supply Voltage","date":"2025-03-05","arxiv_id":"2503.03648","n_code_links":0,"syntology":null},{"paper":null,"title":"An Appearance Defect Detection Method for Cigarettes Based on C-CenterNet","date":"2025-02-10","arxiv_id":"2502.06119","n_code_links":0,"syntology":null},{"paper":null,"title":"Tempus Core: Area-Power Efficient Temporal-Unary Convolution Core for Low-Precision Edge DLAs","date":"2024-12-25","arxiv_id":"2412.19002","n_code_links":0,"syntology":null},{"paper":null,"title":"HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction","date":"2024-11-02","arxiv_id":"2411.01139","n_code_links":0,"syntology":null},{"paper":null,"title":"From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots","date":"2024-10-31","arxiv_id":"2410.23906","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparative-study-of-multiple-deep-learning","title":"A Comparative Study of Multiple Deep Learning Algorithms for Efficient Localization of Bone Joints in the Upper Limbs of Human Body","date":"2024-10-28","arxiv_id":"2410.20639","n_code_links":1,"syntology":null},{"paper":null,"title":"Locally Grouped and Scale-Guided Attention for Dense Pest Counting","date":"2024-08-29","arxiv_id":"2408.16503","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-foundation-models-via-knowledge","title":"Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT","date":"2024-07-25","arxiv_id":"2407.18288","n_code_links":1,"syntology":null},{"paper":"/paper/strengthening-layer-interaction-via-dynamic","title":"Strengthening Layer Interaction via Dynamic Layer Attention","date":"2024-06-19","arxiv_id":"2406.13392","n_code_links":1,"syntology":{"ran":13,"of":14,"unverified":1,"pointer_only":14}},{"paper":null,"title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","date":"2024-06-12","arxiv_id":"2406.08226","n_code_links":0,"syntology":null},{"paper":null,"title":"The impact of deep learning aid on the workload and interpretation accuracy of radiologists on chest computed tomography: a cross-over reader study","date":"2024-06-12","arxiv_id":"2406.08137","n_code_links":0,"syntology":null},{"paper":null,"title":"DLAFormer: An End-to-End Transformer For Document Layout Analysis","date":"2024-05-20","arxiv_id":"2405.11757","n_code_links":0,"syntology":null},{"paper":null,"title":"Prospects of Privacy Advantage in Quantum Machine Learning","date":"2024-05-14","arxiv_id":"2405.08801","n_code_links":0,"syntology":null},{"paper":null,"title":"Fused attention mechanism-based ore sorting network","date":"2024-05-05","arxiv_id":"2405.02785","n_code_links":0,"syntology":null},{"paper":"/paper/yolc-you-only-look-clusters-for-tiny-object","title":"YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images","date":"2024-04-09","arxiv_id":"2404.06180","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-the-robustness-of","title":"Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study","date":"2024-04-04","arxiv_id":"2404.03707","n_code_links":1,"syntology":null},{"paper":"/paper/flightscope-a-deep-comprehensive-assessment","title":"FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery","date":"2024-04-03","arxiv_id":"2404.02877","n_code_links":1,"syntology":null},{"paper":"/paper/rodla-benchmarking-the-robustness-of-document","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","date":"2024-03-21","arxiv_id":"2403.14442","n_code_links":1,"syntology":null},{"paper":null,"title":"Delving into Decision-based Black-box Attacks on Semantic Segmentation","date":"2024-02-02","arxiv_id":"2402.01220","n_code_links":0,"syntology":null},{"paper":null,"title":"Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection","date":"2024-02-02","arxiv_id":"2402.01287","n_code_links":0,"syntology":null},{"paper":"/paper/ecc-polypdet-enhanced-centernet-with","title":"ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection","date":"2024-01-10","arxiv_id":"2401.04961","n_code_links":1,"syntology":null},{"paper":null,"title":"Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Series","date":"2023-11-13","arxiv_id":"2311.07744","n_code_links":0,"syntology":null},{"paper":"/paper/dcqa-document-level-chart-question-answering","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","date":"2023-10-29","arxiv_id":"2310.18983","n_code_links":1,"syntology":null},{"paper":null,"title":"CIR at the NTCIR-17 ULTRE-2 Task","date":"2023-10-18","arxiv_id":"2310.11852","n_code_links":0,"syntology":null},{"paper":null,"title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","date":"2023-10-11","arxiv_id":"2310.07325","n_code_links":0,"syntology":null},{"paper":null,"title":"Randomize to Generalize: Domain Randomization for Runway FOD Detection","date":"2023-09-23","arxiv_id":"2309.13264","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":38},{"task":"/task/object-detection-1","name":"object-detection","papers":34},{"task":"/task/object","name":"Object","papers":21},{"task":"/task/document-layout-analysis","name":"Document Layout Analysis","papers":17},{"task":"/task/object-tracking","name":"Object Tracking","papers":8},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","papers":7},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":6},{"task":"/task/multi-object-tracking","name":"Multi-Object Tracking","papers":5},{"task":"/task/multiple-object-tracking","name":"Multiple Object Tracking","papers":5},{"task":"/task/pose-estimation","name":"Pose Estimation","papers":5},{"task":"/task/image-classification","name":"Image Classification","papers":4},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition","papers":4},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/decoder","name":"Decoder","papers":3},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":3},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":3},{"task":"/task/keypoint-detection","name":"Keypoint Detection","papers":3},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":3},{"task":"/task/representation-learning","name":"Representation Learning","papers":3}],"tasks_shown":20,"n_tasks":136,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":2},{"year":"2019","papers":8},{"year":"2020","papers":9},{"year":"2021","papers":17},{"year":"2022","papers":14},{"year":"2023","papers":18},{"year":"2024","papers":19},{"year":"2025","papers":6}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dla"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}