Search Results for author:
Found 14 papers, 11 papers with code
Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller(GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes.
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
Instead of directly feeding consecutive frames into a VSR model, we propose to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference.
Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search
It is able to find top 0. 16\% and 0. 29\% architectures on average on two search spaces under the budget of only 50 models.
Automated Progressive Learning for Efficient Training of Vision Transformers
First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.
Beyond Fixation: Dynamic Window Visual Transformer
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window.
Dynamic Slimmable Denoising Network
Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images.
DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
We attribute this ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift.
Joint Depth and Normal Estimation from Real-world Time-of-flight Raw Data
We present a novel approach to joint depth and normal estimation for time-of-flight (ToF) sensors.
Dynamic Slimmable Network
Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.
Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation
Remarkably, the performance of our searched architectures has exceeded the teacher model, demonstrating the practicability of our method.
Density Map Guided Object Detection in Aerial Images
Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that the object density map of an image presents how objects distribute in terms of the pixel intensity of the map.
Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
Ranked #1 on
Neural Architecture Search
on CIFAR-100
(Top-1 Error Rate metric)
