Methods › Computer Vision › Object Detection Models › Cascade R-CNN
Cascade R-CNN
Introduced by Zhaowei Cai et al. in Cascade R-CNN: Delving into High Quality Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Cascade R-CNN is an object detection architecture that seeks to address problems with degrading performance with increased IoU thresholds (due to overfitting during training and inference-time mismatch between IoUs for which detector is optimal and the inputs). It is a multi-stage extension of the R-CNN, where detector stages deeper into the cascade are sequentially more selective against close false positives. The cascade of R-CNN stages are trained sequentially, using the output of one stage to train the next. This is motivated by the observation that the output IoU of a regressor is almost invariably better than the input IoU.
Cascade R-CNN does not aim to mine hard negatives. Instead, by adjusting bounding boxes, each stage aims to find a good set of close false positives for training the next stage. When operating in this manner, a sequence of detectors adapted to increasingly higher IoUs can beat the overfitting problem, and thus be effectively trained. At inference, the same cascade procedure is applied. The progressively improved hypotheses are better matched to the increasing detector quality at each stage.
In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.
From the lookup's note on this name: Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “Cascade R-CNN: Delving into High Quality Object Detection” (arXiv:1712.00726, 6,418 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:1712.00726: its page on this site · ask the lookup about it.
Near matches the lookup lists, each a different name: hybrid Multi-Task Cascaded CNN with FaceNet Embeddings; CNN-MV; 3D CNN; CASCADE; msf-CNN; CASCADE; Cascade; Path-CNN.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 34 · with a code link: 20 · where Syntology ran a sample: 8 (6 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (8 of 34 tagged: 6 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 34 of 34, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
AI-Driven MRI Spine Pathology Detection: A Comprehensive Deep Learning Approach for Automated Diagnosis in Diverse Clinical Settings 26 Mar 2025 · 0 repositories · arXiv:2503.20316
-
Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery 27 Jul 2024 · 0 repositories · arXiv:2407.19184
-
On Feasibility of Intent Obfuscating Attacks 22 Jul 2024 · 1 repository · arXiv:2408.02674
-
FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method 28 Apr 2024 · 0 repositories · arXiv:2404.18245
-
Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images 1 Dec 2023 · 1 repository · arXiv:2312.00699
-
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch 24 May 2023 · 1 repository · arXiv:2305.14813
-
Context-Aware Chart Element Detection 7 May 2023 · 1 repository · arXiv:2305.04151
-
FQDet: Fast-converging Query-based Detector 5 Oct 2022 · 2 repositories · arXiv:2210.02318Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers 13 Sep 2022 · 0 repositories · arXiv:2209.05654
-
Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery 16 May 2022 · 0 repositories · arXiv:2205.08002
-
Self-Normalized Density Map (SNDM) for Counting Microbiological Objects 15 Mar 2022 · 0 repositories · arXiv:2203.09474
-
Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagery 18 Jan 2022 · 0 repositories · arXiv:2201.07124
-
Automatic Detection of Injection and Press Mold Parts on 2D Drawing Using Deep Neural Network 22 Oct 2021 · 0 repositories · arXiv:2110.11593
-
Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery 10 Oct 2021 · 0 repositories · arXiv:2110.04906
-
Instances as Queries 5 May 2021 · 5 repositories · arXiv:2105.01928Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection 8 Mar 2021 · 1 repository · arXiv:2103.04507
-
Augmenting Proposals by the Detector Itself 28 Jan 2021 · 0 repositories · arXiv:2101.11789
-
SyNet: An Ensemble Network for Object Detection in UAV Images 23 Dec 2020 · 1 repository · arXiv:2012.12991
-
Hierarchical Context Embedding for Region-based Object Detection 4 Aug 2020 · 0 repositories · arXiv:2008.01338
-
A Solution to Product detection in Densely Packed Scenes 23 Jul 2020 · 2 repositories · arXiv:2007.11946
-
Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization 1 Jun 2020 · 1 repository
-
PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy 10 Mar 2020 · 0 repositories · arXiv:2003.04541
-
Side-Aware Boundary Localization for More Precise Object Detection 9 Dec 2019 · 3 repositories · arXiv:1912.04260
-
IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector 15 Oct 2019 · 0 repositories · arXiv:1910.06573
-
CBNet: A Novel Composite Backbone Network Architecture for Object Detection 9 Sep 2019 · 6 repositories · arXiv:1909.03625Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting 21 Aug 2019 · 3 repositories · arXiv:1908.07801
-
Deep High-Resolution Representation Learning for Visual Recognition 20 Aug 2019 · 42 repositories · arXiv:1908.07919Syntology 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (of 34 harvested samples) · 21 pointer-only (licence)
-
Rethinking Classification and Localization for Cascade R-CNN 27 Jul 2019 · 0 repositories · arXiv:1907.11914
-
Cascade R-CNN: High Quality Object Detection and Instance Segmentation 24 Jun 2019 · 4 repositories · arXiv:1906.09756
-
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks 23 May 2019 · 3 repositories · arXiv:1905.09646Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond 25 Apr 2019 · 9 repositories · arXiv:1904.11492
-
Hybrid Task Cascade for Instance Segmentation 22 Jan 2019 · 5 repositories · arXiv:1901.07518Syntology community repositories only · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples)
-
Acquisition of Localization Confidence for Accurate Object Detection 30 Jul 2018 · 4 repositories · arXiv:1807.11590Syntology community repositories only · 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 18 harvested samples) · 2 pointer-only (licence)
-
Cascade R-CNN: Delving into High Quality Object Detection 3 Dec 2017 · 8 repositories · arXiv:1712.00726Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 41 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections