Try   HackMD

DETR

  • treat the problem as a direct set prediction problem.
  • it is pointed out that both self-attention is especially suitable for the constraints of set prediction.
  • architecture: encode-decoder transformer (with non-autoregressive parallel decoding), set-based global loss (bipartite matching for computing loss, where loss is permutation-invariant).

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

  • bipartite matching losses for set prediction, encode-decoder architectures based on transformer, parallel decoding, and object detection methods.

Set Prediction

  • the most basic form of set prediction would be a multi-class classification task (one vs one, one vs all strategies).
  • direct set-prediction problem needs global inference schemes that model interactions between all predicted elements to avoid redundancy.
  • auto-regressive models are the commonly used models.
Last changed by 
 
meta-learning
meta-learning
0
212

Read more

MetaDet

introduces a weight prediction model to predict the model parameters from its few-shot parameters. the meta-learning strategy is designed to disentangle the learning of class-agnostic and class-specific weight parameters. this work focuses on weight parameter generation/prediction for the detector network (box head) by learning a meta-model that regresses the class-specific parameters trained from few-shot to class-specific parameters trained from large base classes. Training in the first stage, a detector is trained on large base classes, specifically to learn the class-agnostic parameters. in the second stage, only the class-specific parameters are learned while the class-agnostic parameters are fixed. The meta model T is trained by receiving the class-specific weights in the last layer and class-specific weights from few-shot training as inputs, where T is parameterized by the class-agnostic weights. Loss function for training T is:

Dec 20, 2021
RepMet

this work proposes a DML architecture for both image classification and detection in the few-shot scenario.

Dec 19, 2021
A Comparative Review of Few-Shot Object Detection

this is by far the only survey that systematically compares few-shot object detection methods. Taxonomy (based on dataset settings) In terms of novel classes, the problems can be defined as: LS-FSOD: a small novel set data and an optional dataset without target supervision to learn generic notions. SS-FSOD: has an extra target-domain data without annotations (an additional unlabelled examples) WS-FSOD: a small novel set of data with image-level labels (weakly labelled, sometimes some unlaballed novel set and a base set may be included to compensate for the inaccurate supervisory signals) Usually, base is usually for learning task-agnostic notions, where as learning from whether weakly labelled novel set or unlabelled novel set is for learning task-specific guidance

Dec 4, 2021
Weakly Supervised Object Localisation and Detection: A Survey

Dec 3, 2021
Read more from meta-learning
Published on HackMD