research
∙
08/20/2023
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
In this paper, we investigate the adversarial robustness of vision trans...
share
research
∙
07/28/2023
Does Full Waveform Inversion Benefit from Big Data?
This paper investigates the impact of big data on deep learning models f...
research
∙
06/21/2023
𝔼^𝐅𝐖𝐈: Multi-parameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
Elastic geophysical properties (such as P- and S-wave velocities) are of...
research
∙
06/07/2023
Designing a Better Asymmetric VQGAN for StableDiffusion
StableDiffusion is a revolutionary text-to-image generator that is causi...
research
∙
05/25/2023
Image is First-order Norm+Linear Autoregressive
This paper reveals that every image can be understood as a first-order n...
research
∙
02/27/2023
Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) d...
research
∙
02/17/2023
Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression
Automatic image cropping algorithms aim to recompose images like human-b...
research
∙
11/23/2022
Self-Supervised Learning based on Heat Equation
This paper presents a new perspective of self-supervised learning based ...
research
∙
07/31/2022
Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
Generative adversarial networks (GANs) have been trained to be professio...
research
∙
07/07/2022
Should All Proposals be Treated Equally in Object Detection?
The complexity-precision trade-off of an object detector is a critical p...
research
∙
06/07/2022
Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding
Leveraging large-scale data can introduce performance gains on many comp...
research
∙
05/10/2022
Reduce Information Loss in Transformers for Pluralistic Image Inpainting
Transformers have achieved great success in pluralistic image inpainting...
research
∙
04/28/2022
An Intriguing Property of Geophysics Inversion
Inversion techniques are widely used to reconstruct subsurface physical ...
research
∙
04/20/2022
Residual Mixture of Experts
Mixture of Experts (MoE) is able to scale up vision transformers effecti...
research
∙
03/10/2022
The Overlooked Classifier in Human-Object Interaction Recognition
Human-Object Interaction (HOI) recognition is challenging due to two fac...
research
∙
02/03/2022
Exploring Multi-physics with Extremely Weak Supervision
Multi-physical inversion plays a critical role in geophysics. It has bee...
research
∙
12/13/2021
Decoupling Object Detection from Human-Object Interaction Recognition
We propose DEFR, a DEtection-FRee method to recognize Human-Object Inter...
research
∙
12/12/2021
Improving Vision Transformers for Incremental Learning
This paper studies using Vision Transformers (ViT) in class incremental ...
research
∙
10/18/2021
Unsupervised Finetuning
This paper studies "unsupervised finetuning", the symmetrical problem of...
research
∙
10/14/2021
Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
This paper investigates unsupervised learning of Full-Waveform Inversion...
research
∙
08/12/2021
Mobile-Former: Bridging MobileNet and Transformer
We present Mobile-Former, a parallel design of MobileNet and Transformer...
research
∙
08/12/2021
MicroNet: Improving Image Recognition with Extremely Low FLOPs
This paper aims at addressing the problem of substantial performance deg...
research
∙
07/27/2021
Is Object Detection Necessary for Human-Object Interaction Recognition?
This paper revisits human-object interaction (HOI) recognition at image ...
research
∙
07/26/2021
Improve Unsupervised Pretraining for Few-label Transfer
Unsupervised pretraining has achieved great success and many recent work...
research
∙
06/15/2021
Dynamic Head: Unifying Object Detection Heads with Attentions
The complex nature of combining localization and classification in objec...
research
∙
03/19/2021
Dynamic Transfer for Multi-Source Domain Adaptation
Recent works of multi-source domain adaptation focus on learning a domai...
research
∙
03/15/2021
Revisiting Dynamic Convolution via Matrix Decomposition
Recent research in dynamic convolution shows substantial performance boo...
research
∙
02/21/2021
Weak NAS Predictors Are All You Need
Neural Architecture Search (NAS) finds the best network architecture by ...
research
∙
12/10/2020
Are Fewer Labels Possible for Few-shot Learning?
Few-shot learning is challenging due to its very limited data and labels...
research
∙
11/24/2020
MicroNet: Towards Image Recognition with Extremely Low FLOPs
In this paper, we present MicroNet, which is an efficient convolutional ...
research
∙
03/27/2020
DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search
Efficient search is a core issue in Neural Architecture Search (NAS). It...
research
∙
03/22/2020
Dynamic ReLU
Rectified linear units (ReLU) are commonly used in deep neural networks....
research
∙
12/07/2019
Dynamic Convolution: Attention over Convolution Kernels
Light-weight convolutional neural networks (CNNs) suffer performance deg...
research
∙
11/17/2019
Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
Current state-of-the-art object detectors can have significant performan...
research
∙
07/11/2019
Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation
The success of supervised deep learning depends on the training labels. ...
research
∙
05/30/2019
Large Scale Incremental Learning
Modern machine learning suffers from catastrophic forgetting when learni...
research
∙
04/13/2019
Rethinking Classification and Localization in R-CNN
Modern R-CNN based detectors share the RoI feature extractor head for bo...
research
∙
02/02/2018
Incremental Classifier Learning with Generative Adversarial Networks
In this paper, we address the incremental classifier learning problem, w...
research
∙
05/28/2017