Instance Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

36 leaderboard tables shown for this task, 36 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 36 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

111 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 111 until expanded.

Subtasks archive 2025-07-28

17 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 1,158 papers with code (2,262 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Mask R-CNN
  20 Mar 2017 179 repositories listed Syntology ran 42 of 140 samples · 98 unverified · 23 pointer-only (licence)
  Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.
• MMDetection: Open MMLab Detection Toolbox and Benchmark
  17 Jun 2019 142 repositories listed Syntology ran 14 of 82 samples · 68 unverified
  In this paper, we introduce the various features of this toolbox.
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  25 Mar 2021 80 repositories listed Syntology ran 108 of 207 samples · 99 unverified · 43 pointer-only (licence)
  This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision.
• YOLACT: Real-time Instance Segmentation
  4 Apr 2019 48 repositories listed Syntology ran 10 of 21 samples · 11 unverified · 6 pointer-only (licence)
  Then we produce instance masks by linearly combining the prototypes with the mask coefficients.
• Deep High-Resolution Representation Learning for Visual Recognition
  20 Aug 2019 42 repositories listed Syntology ran 3 of 34 samples · 31 unverified · 16 pointer-only (licence)
  High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
• Deep High-Resolution Representation Learning for Human Pose Estimation
  25 Feb 2019 39 repositories listed Syntology ran 8 of 25 samples · 17 unverified
  We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel.
• Microsoft COCO: Common Objects in Context
  1 May 2014 38 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding.
• ResNeSt: Split-Attention Networks
  19 Apr 2020 36 repositories listed Syntology ran 8 of 48 samples · 40 unverified · 23 pointer-only (licence)
  It is well known that featuremap attention and multi-path representation are important for visual recognition.
• YOLACT++: Better Real-time Instance Segmentation
  3 Dec 2019 36 repositories listed Syntology ran 11 of 43 samples · 32 unverified
  Then we produce instance masks by linearly combining the prototypes with the mask coefficients.
• Res2Net: A New Multi-scale Backbone Architecture
  2 Apr 2019 34 repositories listed Syntology ran 3 of 9 samples · 6 unverified · 9 pointer-only (licence)
  We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.
• Non-local Neural Networks
  21 Nov 2017 32 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
• Deformable ConvNets v2: More Deformable, Better Results
  27 Nov 2018 26 repositories listed Syntology ran 2 of 13 samples · 11 unverified · 2 pointer-only (licence)
  The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects.
• SOLO: Segmenting Objects by Locations
  10 Dec 2019 24 repositories listed
  We present a new, embarrassingly simple approach to instance segmentation in images.
• Swin Transformer V2: Scaling Up Capacity and Resolution
  18 Nov 2021 23 repositories listed Syntology ran 3 of 30 samples · 27 unverified
  Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained…
• Towards End-to-End Lane Detection: an Instance Segmentation Approach
  15 Feb 2018 22 repositories listed Syntology ran 3 of 34 samples · 31 unverified · 1 pointer-only (licence)
  By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.
• Visual Attention Network
  20 Feb 2022 21 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
  30 Nov 2017 21 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 3 pointer-only (licence)
  We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs).
• PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
  26 Apr 2022 19 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 1 pointer-only (licence)
  Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems.
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
  19 May 2017 19 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 3 pointer-only (licence)
  Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives.
• SOLOv2: Dynamic and Fast Instance Segmentation
  23 Mar 2020 18 repositories listed Syntology ran 15 of 38 samples · 23 unverified · 24 pointer-only (licence)
  Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
• RTMDet: An Empirical Study of Designing Real-Time Object Detectors
  14 Dec 2022 14 repositories listed Syntology ran 3 of 20 samples · 17 unverified
  In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection.
• PointRend: Image Segmentation as Rendering
  17 Dec 2019 14 repositories listed Syntology ran 5 of 18 samples · 13 unverified
  We present a new method for efficient high-quality image segmentation of objects and scenes.
• Is Heuristic Sampling Necessary in Training Deep Object Detectors?
  11 Sep 2019 14 repositories listed
  In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors.
• Efficient Attention: Attention with Linear Complexities
  4 Dec 2018 14 repositories listed Syntology ran 7 of 8 samples · 1 unverified · 1 pointer-only (licence)
  Dot-product attention has wide applications in computer vision and natural language processing.
• Bottleneck Transformers for Visual Recognition
  27 Jan 2021 13 repositories listed Syntology ran 26 of 49 samples · 23 unverified · 8 pointer-only (licence)
  Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84.
• UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
  11 Dec 2019 13 repositories listed Syntology ran 1 of 9 samples · 8 unverified · 2 pointer-only (licence)
  The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN).
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
  10 Dec 2019 13 repositories listed
  We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
• ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
  8 Oct 2019 13 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance…
• XCiT: Cross-Covariance Image Transformers
  17 Jun 2021 12 repositories listed Syntology ran 3 of 14 samples · 11 unverified · 3 pointer-only (licence)
  We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries.
• Panoptic Feature Pyramid Networks
  8 Jan 2019 12 repositories listed Syntology ran 7 of 12 samples · 5 unverified
  In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.

Syntology lines on 27 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.