Search Results for author:
Found 33 papers, 17 papers with code
$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
To address the robustness problem, we first benchmark different NAS methods under a wide range of proxy data, proxy channels, proxy layers and proxy epochs, since the robustness of NAS under different kinds of proxies has not been explored before.
Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation
To enhance the model, adaptability between domains and reduce the computational cost when deploying the ensemble model, we propose a novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model.
ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations.
Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing
In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training strategy to strengthen the performance of residual networks.
Effective Invertible Arbitrary Image Rescaling
To increase its real world applicability, numerous models have also been proposed to restore SR images with arbitrary scale factors, including asymmetric ones where images are resized to different scales along horizontal and vertical directions.
Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation
In this paper, we intend to search an optimal network structure that can run in real-time for this problem.
Field-aware Variational Autoencoders for Billion-scale User Representation Learning
Moreover, we deploy the proposed method in real-world applications and conduct online A/B tests in a look-alike system.
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
In this paper, we discover for the first time that both efficient DNNs and their lottery subnetworks (i. e., lottery tickets) can be directly identified from a supernet, which we term as SuperTickets, via a two-in-one training scheme with jointly architecture searching and parameter pruning.
Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification
Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences.
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
To this end, this work advocates hybrid NNs that consist of both powerful yet costly multiplications and efficient yet less powerful operators for marrying the best of both worlds, and proposes ShiftAddNAS, which can automatically search for more accurate and more efficient NNs.
Towards Robust Adaptive Object Detection under Noisy Annotations
Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate the target labels with the given target domain images.
$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically.
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel.
b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search (NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural network automatically.
Exploring Gradient Flow Based Saliency for DNN Model Compression
Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead.
BN-NAS: Neural Architecture Search with Batch Normalization
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS).
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #437 on
Image Classification
on ImageNet
AutoSampling: Search for Effective Data Sampling Schedules
Data sampling acts as a pivotal role in training deep learning models.
Action Segmentation with Mixed Temporal Domain Adaptation
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning.
Ranked #8 on
Action Segmentation
on Breakfast
No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE
Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms.
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution
First, we design a cross-task distillation scheme that encourages DSR and DE networks to learn from each other in a teacher-student role-exchanging fashion.
MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground truth labels to fully leverage unlabeled target data for model adaptation.
Ranked #29 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
AutoPruning for Deep Neural Network with Dynamic Channel Masking
In the process of pruning, we utilize a searchable hyperparameter, remaining ratio, to denote the number of channels in each convolution layer, and then a dynamic masking process is proposed to describe the corresponding channel evolution.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure
Besides, we propose a new MOT evaluation measure, Still Another IDF score (SAIDF), aiming to focus more on identity issues. This new measure may overcome some problems of the previous measures and provide a better insight for identity issues in MOT.
Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections.
UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory.
Ranked #8 on
Action Segmentation
on GTEA
Cross-modality Person re-identification with Shared-Specific Feature Transfer
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
