Related papers: Self-Balanced R-CNN for Instance Segmentation

Self-Balanced R-CNN for Instance Segmentation

URL: http://arxiv.org/abs/2404.16633v1
Date: Thu, 25 Apr 2024 14:22:44 GMT
Title: Self-Balanced R-CNN for Instance Segmentation
Abstract summary: Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) during the training of the second stage. Our Self-Balanced R-CNN model brings brand new loop mechanisms of bounding box and mask refinements.
Score: 2.059150828428537
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) during the training of the second stage. Our Self-Balanced R-CNN (SBR-CNN), an evolved version of the Hybrid Task Cascade (HTC) model, brings brand new loop mechanisms of bounding box and mask refinements. With an improved Generic RoI Extraction (GRoIE), we also address the feature-level imbalance at the Feature Pyramid Network (FPN) level, originated by a non-uniform integration between low- and high-level features from the backbone layers. In addition, the redesign of the architecture heads toward a fully convolutional approach with FCC further reduces the number of parameters and obtains more clues to the connection between the task to solve and the layers used. Moreover, our SBR-CNN model shows the same or even better improvements if adopted in conjunction with other state-of-the-art models. In fact, with a lightweight ResNet-50 as backbone, evaluated on COCO minival 2017 dataset, our model reaches 45.3% and 41.5% AP for object detection and instance segmentation, with 12 epochs and without extra tricks. The code is available at https://github.com/IMPLabUniPr/mmdetection/tree/sbr_cnn

Related papers

Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems [0.0]
We present a rank-aware decomposition applicable to the dominant interaction mechanisms in recommender systems.<n>The decomposition moves context-only computation from once-per-candidate to once-per-request, identity-equivalent to the original model.<n> Applied to a production DLRM-style ranker without any architectural change, the decomposition increases per-pod throughput by 87.5%.
arXiv Detail & Related papers (2026-05-24T13:35:36Z)
Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation [0.0]
This paper introduces the N-Way Self-Evaluating Deliberation (NSED) protocol, a Mixture-of-Models (MoM) architecture that constructs emergent composite models from a plurality of distinct expert agents.<n>Unlike traditional Mixture-of-Experts (MoE) which rely on static gating networks, NSED employs a Dynamic Expertise Broker that treats model selection as a variation of the Knapsack Problem.
arXiv Detail & Related papers (2026-01-23T16:11:54Z)
Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
arXiv Detail & Related papers (2025-09-22T15:13:14Z)
MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification [14.221889446444433]
We introduce Multi-Scale and Attention Convolutional Neural Network (MSA-CNN), a lightweight architecture featuring as few as 10,000 parameters. Model complexity is further reduced by separating temporal and spatial feature extraction and using cost-effective global spatial convolutions. Our evaluation, based on repeated cross-validation and re-evaluation of all baseline models, demonstrated that the large MSA-CNN outperformed all baseline models on all three datasets in terms of accuracy and Cohen's kappa.
arXiv Detail & Related papers (2025-01-06T11:46:02Z)
Attention Beats Linear for Fast Implicit Neural Representation Generation [13.203243059083533]
We propose Attention-based Localized INR (ANR) composed of a localized attention layer (LAL) and a global representation vector. With instance-specific representation and instance-agnostic ANR parameters, the target signals are well reconstructed as a continuous function.
arXiv Detail & Related papers (2024-07-22T03:52:18Z)
Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis [93.0013343535411]
We propose a novel type of analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim) We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy. Results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance.
arXiv Detail & Related papers (2023-06-16T18:29:26Z)
Improved Convergence Guarantees for Shallow Neural Networks [91.3755431537592]
We prove convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Our model has the following features: regression with quadratic loss function, fully connected feedforward architecture, RelU activations, Gaussian data instances, adversarial labels. They strongly suggest that, at least in our model, the convergence phenomenon extends well beyond the NTK regime''
arXiv Detail & Related papers (2022-12-05T14:47:52Z)
Towards Stable Co-saliency Detection and Object Co-segmentation [12.979401244603661]
We present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG) We first propose a multi-path stable recurrent unit (MSRU), containing dummy orders mechanisms (DOM) and recurrent unit (RU) Our proposed MSRU not only helps CoSOD (CoSEG) model captures robust inter-image relations, but also reduces order-sensitivity, resulting in a more stable inference and training process.
arXiv Detail & Related papers (2022-09-25T03:58:49Z)
A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation [68.10621089649486]
We propose Attention Aggregation based Feature Pyramid Network (A2-FPN) to improve multi-scale feature learning. A2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.
arXiv Detail & Related papers (2021-05-07T11:51:08Z)
A Fully Tensorized Recurrent Neural Network [48.50376453324581]
We introduce a "fully tensorized" RNN architecture which jointly encodes the separate weight matrices within each recurrent cell. This approach reduces model size by several orders of magnitude, while still maintaining similar or better performance compared to standard RNNs.
arXiv Detail & Related papers (2020-10-08T18:24:12Z)
Iterative Network for Image Super-Resolution [69.07361550998318]
Single image super-resolution (SISR) has been greatly revitalized by the recent development of convolutional neural networks (CNN) This paper provides a new insight on conventional SISR algorithm, and proposes a substantially different approach relying on the iterative optimization. A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
arXiv Detail & Related papers (2020-05-20T11:11:47Z)
Model Fusion via Optimal Transport [64.13185244219353]
We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
arXiv Detail & Related papers (2019-10-12T22:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.