Corpus ID: 236428500

Rank & Sort Loss for Object Detection and Instance Segmentation

  title={Rank \& Sort Loss for Object Detection and Instance Segmentation},
  author={Kemal Oksuz and Baris Can Cam and Emre Akbas and Sinan Kalkan},
S3. More Experiments on RS Loss 5 S3.1. Effect of δRS , the Single Hyper-parameter, for RS Loss. . . . . . . . . . . . . . . . . 5 S3.2. Training Cascade R-CNN [1] with RS Loss 5 S3.3. Hyper-parameters of R-CNN Variants in Table 1 of the Paper . . . . . . . . . . . . 5 S3.4. Using Different Localisation Qualities as Continuous Labels to Supervise Instance Segmentation Methods . . . . . . . . . . 5 S3.5. Details of the Ablation Analysis on Different Degrees of Imbalance . . . . . . . . . 6 S3.6… Expand
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
MaIoU, a Mask-aware Intersection-over-Union for assigning anchor boxes as positives and negatives during training of instance segmentation methods that consistently measures the proximity of an anchor box with not only a ground truth box but also its associated ground truth mask, enables a more accurate supervision during training. Expand
Mask Transfiner for High-Quality Instance Segmentation
Instead of operating on regular dense tensors, the Mask Transfiner decomposes and represents the image regions as a quadtree, which allows it to predict highly accurate instance masks, at a low computational cost. Expand


Libra R-CNN: Towards Balanced Learning for Object Detection
Libra R-CNN is proposed, a simple but effective framework towards balanced learning for object detection that integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level. Expand
D2Det: Towards High Quality Object Detection and Instance Segmentation
A novel two-stage detection method, D2Det, that collectively addresses both precise localization and accurate classification is proposed and a discriminative RoI pooling scheme that samples from various sub-regions of a proposal and performs adaptive weighting to obtain discriminating features is introduced. Expand
Cascade R-CNN: Delving Into High Quality Object Detection
A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset, and experiments show that it is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. Expand
Mask Scoring R-CNN
This paper proposes Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks and calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. Expand
CenterMask: Single Shot Instance Segmentation With Point Representation
This paper decomposes the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
LVIS: A Dataset for Large Vocabulary Instance Segmentation
This work introduces LVIS (pronounced ‘el-vis’): a new dataset for Large Vocabulary Instance Segmentation, which has a long tail of categories with few training samples due to the Zipfian distribution of categories in natural images. Expand
Training Region-Based Object Detectors with Online Hard Example Mining
OHEM is a simple and intuitive algorithm that eliminates several heuristics and hyperparameters in common use that leads to consistent and significant boosts in detection performance on benchmarks like PASCAL VOC 2007 and 2012. Expand
FCOS: Fully Convolutional One-Stage Object Detection
For the first time, a much simpler and flexible detection framework achieving improved detection accuracy is demonstrated, and it is hoped that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Expand
AP-Loss for Accurate One-Stage Object Detection
A novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem is proposed, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. Expand