Search Results for author:
Found 9 papers, 4 papers with code
Supervised Contrastive Learning on Blended Images for Long-tailed Recognition
The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model.
Ranked #19 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
MAC-DO: An Efficient Output-Stationary GEMM Accelerator for CNNs Using DRAM Technology
Furthermore, a MAC-DO array efficiently reuses three types of data (input, weight and output), minimizing data movement.
Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos
To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.
Improving Few-shot Learning with Weakly-supervised Object Localization
In this work, we propose a novel framework that generates class representations by extracting features from class-relevant regions of the images.
Few-shot Open-set Recognition by Transformation Consistency
Based on the transformation consistency, our method measures the difference between the transformed prototypes and a modified prototype set.
Meta Batch-Instance Normalization for Generalizable Person Re-Identification
To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers.
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation.
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
