Search Results for author:
Found 11 papers, 7 papers with code
Dense Vision Transformer Compression with Few Samples
In particular, the issue of sparse compression exists in traditional CNN few-shot methods, which can only produce very few compressed models of different model sizes.
Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm
For 22% latency reduction, it surpasses previous methods by on average 7 percentage points on ImageNet-1k.
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder.
How to Reduce Change Detection to Semantic Segmentation
And most segmentation networks can be adapted to solve the CD problems with our MTF module.
Ranked #1 on
Change Detection
on PCD
R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning
However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels in the deep learning paradigm.
PENCIL: Deep Learning with Noisy Labels
It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and accuracies drop dramatically.
Practical Network Acceleration with Tiny Sets
Previous methods mainly adopt filter-level pruning to accelerate networks with scarce training samples.
Distilling Knowledge by Mimicking Features
We argue that the teacher should give more freedom to the student feature's magnitude, and let the student pay more attention on mimicking the feature direction.
Ranked #1 on
Knowledge Distillation
on MS COCO
(mAP metric)
A Hierarchical Location Normalization System for Text
We propose a system named ROIBase that normalizes the text by the Chinese hierarchical administrative divisions.
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
In this paper, we propose a principled end-to-end framework named deep decipher (D2) for SSL.
A Dynamic Evolutionary Framework for Timeline Generation based on Distributed Representations
Given the collection of timestamped web documents related to the evolving topic, timeline summarization (TS) highlights its most important events in the form of relevant summaries to represent the development of a topic over time.
