Search Results for author:
Found 7 papers, 3 papers with code
Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification
To learn camera-view invariant features for person Re-IDentification (Re-ID), the cross-camera image pairs of each person play an important role.
SATS: Self-Attention Transfer for Continual Semantic Segmentation
Considering that pixels belonging to the same class in each image often share similar visual properties, a class-specific region pooling is applied to provide more efficient relationship information for knowledge transfer.
Ranked #1 on
Overlapped 25-25
on ADE20K
Learning Discriminative Prototypes with Dynamic Time Warping
We propose Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific discriminative prototypes for temporal recognition tasks.
Disjoint Label Space Transfer Learning with Common Factorised Space
In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model.
Ranked #19 on
Unsupervised Domain Adaptation
on Market to Duke
Multi-Level Factorisation Net for Person Re-Identification
Key to effective person re-identification (Re-ID) is modelling discriminative and view-invariant factors of person appearance at both high and low semantic levels.
The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
Many vision problems require matching images of object instances across different domains.
Scalable and Effective Deep CCA via Soft Decorrelation
Specifically, exact decorrelation is replaced by soft decorrelation via a mini-batch based Stochastic Decorrelation Loss (SDL) to be optimised jointly with the other training objectives.
