Hierarchical Transferability Calibration Network (HTCN) is an adaptive object detector that hierarchically (local-region/image/instance) calibrates the transferability of feature representations for harmonizing transferability and discriminability. The proposed model consists of three components: (1) Importance Weighted Adversarial Training with input Interpolation (IWAT-I), which strengthens the global discriminability by re-weighting the interpolated image-level features; (2) Context-aware Instance-Level Alignment (CILA) module, which enhances the local discriminability by capturing the complementary effect between the instance-level feature and the global context information for the instance-level feature alignment; (3) local feature masks that calibrate the local transferability to provide semantic guidance for the following discriminative pattern alignment.
Source: Harmonizing Transferability and Discriminability for Adapting Object DetectorsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Clustering | 1 | 11.11% |
Deep Clustering | 1 | 11.11% |
Audio Source Separation | 1 | 11.11% |
Music Source Separation | 1 | 11.11% |
Time Series Analysis | 1 | 11.11% |
Action Segmentation | 1 | 11.11% |
Decoder | 1 | 11.11% |
Object Detection | 1 | 11.11% |
Weakly Supervised Object Detection | 1 | 11.11% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |