Corpus ID: 236428500

Rank & Sort Loss for Object Detection and Instance Segmentation

@article{Oksuz2021RankS,
  title={Rank \& Sort Loss for Object Detection and Instance Segmentation},
  author={Kemal Oksuz and Baris Can Cam and Emre Akbas and Sinan Kalkan},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.11669}
}
We propose Rank & Sort (RS) Loss, as a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.) their continuous localisation qualities (e.g. Intersection-over-Union IoU). To tackle the non-differentiable nature of ranking and sorting, we reformulate the… Expand

References

SHOWING 1-10 OF 47 REFERENCES
AP-Loss for Accurate One-Stage Object Detection
TLDR
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
Bounding Box Regression With Uncertainty for Accurate Object Detection
TLDR
A novel bounding box regression loss that greatly improves the localization accuracies of various architectures with nearly no additional computation and allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the globalization performance. Expand
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
TLDR
This work makes the first attempt to discover new loss functions for the challenging object detection from primitive operation levels and finds the searched losses are insightful. Expand
LVIS: A Dataset for Large Vocabulary Instance Segmentation
TLDR
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
D2Det: Towards High Quality Object Detection and Instance Segmentation
TLDR
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
TLDR
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
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand
Is Sampling Heuristics Necessary in Training Deep Object Detectors
TLDR
This paper proposes a guided loss scaling technique to control the classification loss during training, without using any hyper-parameter, and proposes an adaptive thresholding technique to refine predictions during inference, which constitute the Sampling-Free mechanism. Expand
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
TLDR
Improved representations of quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations are designed. Expand
...
1
2
3
4
5
...