121 citations · 236 across the 16 of their papers we have counts for
16 papers · 1 filter
Diffusion Models as Masked Autoencoders
Chen Wei, Karttikeya Mangalam, Po-Yao Huang +7
There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representati…
Ego-Only: Egocentric Action Detection without Exocentric Transferring
Huiyu Wang, Mitesh Kumar Singh, Lorenzo Torresani
We present Ego-Only, the first approach that enables state-of-the-art action detection on egocentric (first-person) videos without any form of exocentric (third-person) transferrin…
Unleashing the Power of Visual Prompting At the Pixel Level
Junyang Wu, Xianhang Li, Chen Wei +4
This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rath…
SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training
Yuanze Lin, Chen Wei, Huiyu Wang +2
Video-language pre-training is crucial for learning powerful multi-modal representation. However, it typically requires a massive amount of computation. In this paper, we develop S…
Masked Autoencoders Enable Efficient Knowledge Distillers
Yutong Bai, Zeyu Wang, Junfei Xiao +5
This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel recons…
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qihang Yu, Huiyu Wang, Dahun Kim +6
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer archi…
A Simple Data Mixing Prior for Improving Self-Supervised Learning
Sucheng Ren, Huiyu Wang, Zhengqi Gao +4
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervise…
In Defense of Image Pre-Training for Spatiotemporal Recognition
Xianhang Li, Huiyu Wang, Chen Wei +4
Image pre-training, the current de-facto paradigm for a wide range of visual tasks, is generally less favored in the field of video recognition. By contrast, a common strategy is t…
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
Feng Wang, Huiyu Wang, Chen Wei +2
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed informati…
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Huiyu Wang, Yukun Zhu, Bradley Green +3
Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prov…
Rethinking Normalization and Elimination Singularity in Neural Networks
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
In this paper, we study normalization methods for neural networks from the perspective of elimination singularity. Elimination singularities correspond to the points on the trainin…
Localizing Occluders with Compositional Convolutional Networks
Adam Kortylewski, Qing Liu, Huiyu Wang +2
Compositional convolutional networks are generative compositional models of neural network features, that achieve state of the art results when classifying partially occluded objec…
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion
Adam Kortylewski, Qing Liu, Huiyu Wang +2
Deep convolutional neural networks (DCNNs) are powerful models that yield impressive results at object classification. However, recent work has shown that they do not generalize we…
Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
Qing Liu, Lingxi Xie, Huiyu Wang +1
Sketch-based image retrieval (SBIR) is widely recognized as an important vision problem which implies a wide range of real-world applications. Recently, research interests arise in…
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typical…
ELASTIC: Improving CNNs with Dynamic Scaling Policies
Huiyu Wang, Aniruddha Kembhavi, Ali Farhadi +2
Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have a similar theme: a set of intuitive and manually…