204 citations · 490 across the 18 of their papers we have counts for
18 papers
MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition
Xinyu Gong, Sreyas Mohan, Naina Dhingra +4
In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG). MMG aims to study how systems can generalize when data…
NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes
Zhiwen Fan, Peihao Wang, Yifan Jiang +3
Neural volumetric representations have shown the potential that Multi-layer Perceptrons (MLPs) can be optimized with multi-view calibrated images to represent scene geometry and ap…
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
Wuyang Chen, Wei Huang, Xinyu Gong +2
Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity…
Unified Implicit Neural Stylization
Zhiwen Fan, Yifan Jiang, Peihao Wang +3
Representing visual signals by implicit representation (e.g., a coordinate based deep network) has prevailed among many vision tasks. This work explores a new intriguing direction:…
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Yifan Jiang, Xinyu Gong, Junru Wu +3
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often co…
Searching for Two-Stream Models in Multivariate Space for Video Recognition
Xinyu Gong, Heng Wang, Zheng Shou +3
Conventional video models rely on a single stream to capture the complex spatial-temporal features. Recent work on two-stream video models, such as SlowFast network and AssembleNet…
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
Wuyang Chen, Xinyu Gong, Junru Wu +5
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS…
SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization
Aaditya Singh, Shreeshail Hingane, Xinyu Gong +1
Artistic style transfer aims to transfer the style characteristics of one image onto another image while retaining its content. Existing approaches commonly leverage various normal…
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Wuyang Chen, Xinyu Gong, Zhangyang Wang
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intens…
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity
Xinyu Gong, Wuyang Chen, Tianlong Chen +1
We present Sandwich Batch Normalization (SaBN), a frustratingly easy improvement of Batch Normalization (BN) with only a few lines of code changes. SaBN is motivated by addressing…
AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
Xinyu Gong, Wuyang Chen, Yifan Jiang +5
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards ac…
NADS: Neural Architecture Distribution Search for Uncertainty Awareness
Randy Ardywibowo, Shahin Boluki, Xinyu Gong +2
Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. It becomes im…
AutoSpeech: Neural Architecture Search for Speaker Recognition
Shaojin Ding, Tianlong Chen, Xinyu Gong +2
Speaker recognition systems based on Convolutional Neural Networks (CNNs) are often built with off-the-shelf backbones such as VGG-Net or ResNet. However, these backbones were orig…
FasterSeg: Searching for Faster Real-time Semantic Segmentation
Wuyang Chen, Xinyu Gong, Xianming Liu +3
We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neura…
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
Xinyu Gong, Shiyu Chang, Yifan Jiang +1
Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the first preliminary st…
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Yifan Jiang, Xinyu Gong, Ding Liu +6
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As o…
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Rui Liu, Yu Liu, Xinyu Gong +2
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditiona…
Neural Stereoscopic Image Style Transfer
Xinyu Gong, Haozhi Huang, Lin Ma +3
Neural style transfer is an emerging technique which is able to endow daily-life images with attractive artistic styles. Previous work has succeeded in applying convolutional neura…