Search Results for author:
Found 9 papers, 4 papers with code
Benchmarking Detection Transfer Learning with Vision Transformers
The complexity of object detection methods can make this benchmarking non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive.
Metric Learning with Adaptive Density Discrimination
Beyond classification, we further validate the saliency of the learnt representations via their attribute concentration and hierarchy recovery properties, achieving 10-25% relative gains on the softmax classifier and 25-50% on triplet loss in these tasks.
Learning to Segment Object Candidates
Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier.
Microsoft COCO Captions: Data Collection and Evaluation Server
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
Local Decorrelation For Improved Pedestrian Detection
In fact, orthogonal trees with our locally decorrelated features outperform oblique trees trained over the original features at a fraction of the computational cost.
Ranked #32 on
Pedestrian Detection
on Caltech
Detecting Objects using Deformation Dictionaries
Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes.
Layered Logic Classifiers: Exploring the `And' and `Or' Relations
Many the solutions to the problem require to perform logic operations such as `and', `or', and `not'.
Exploring Weak Stabilization for Motion Feature Extraction
We describe novel but simple motion features for the problem of detecting objects in video sequences.
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection
Our features, called sketch tokens, are learned using supervised mid-level information in the form of hand drawn contours in images.
