Search Results for author:
Found 24 papers, 17 papers with code
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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
DeViT: Deformed Vision Transformers in Video Inpainting
This paper proposes a novel video inpainting method.
Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers
Despite the success, its development and application on self-supervised vision transformers have been hindered by several barriers, including the high search cost, the lack of supervision, and the unsuitable search space.
H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions
The learnt deformable kernel is then utilized in convolving the input frames for predicting the interpolated frame.
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input image.
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
To address this issue, we propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model's ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence.
Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification
In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect.
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
Compared with the existing methods, GrowCLIP improves 2. 3% average top-1 accuracy on zero-shot image classification of 9 downstream tasks.
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages.
DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions
Addressing this problem, we modularize a large search space into blocks with small search spaces and develop a family of models with the distilling neural architecture (DNA) techniques.
Perception-Oriented Video Frame Interpolation via Asymmetric Blending
In practice, motion estimates often prove to be error-prone, resulting in misaligned features.
