Search Results for author:
Found 21 papers, 11 papers with code
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN).
Cut and Learn for Unsupervised Object Detection and Instance Segmentation
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models.
Ranked #1 on
Unsupervised Instance Segmentation
on UVO
SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator
Named after the fossils of one of the oldest known human ancestors, our LUCY dataset contains high-quality Computed Tomography (CT) scans of the complete human head before and after orthognathic surgeries, critical for evaluating surgery results.
Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech
Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features.
Debiased Learning from Naturally Imbalanced Pseudo-Labels
Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data.
Ranked #1 on
Semi-Supervised Image Classification
on ImageNet - 0.2% labeled data
(using extra training data)
Hankel-structured Tensor Robust PCA for Multivariate Traffic Time Series Anomaly Detection
We treat the raw data with anomalies as a multivariate time series matrix (location $\times$ time) and assume the denoised matrix has a low-rank structure.
Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
Intuitively, no matter what the downstream task is, instances to be labeled must be representative and diverse: The former would facilitate label propagation to unlabeled data, whereas the latter would ensure coverage of the entire dataset.
Active Learning
Semi-Supervised Image Classification (Cold Start)
Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices
Moreover, to prevent the compact model from forgetting the knowledge of the source data during knowledge distillation, a collaborative knowledge distillation (Co-KD) method is developed to unify the source data on the server and the target data on the edge device to train the compact model.
Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers
Hyperbolic space can naturally embed hierarchies, unlike Euclidean space.
FedNILM: Applying Federated Learning to NILM Applications at the Edge
Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring.
Low-Rank Hankel Tensor Completion for Traffic Speed Estimation
This paper studies the traffic state estimation (TSE) problem using sparse observations from mobile sensors.
Unsupervised Visual Attention and Invariance for Reinforcement Learning
Existing methods focus on training an RL policy that is universal to changing visual domains, whereas we focus on extracting visual foreground that is universal, feeding clean invariant vision to the RL policy learner.
A Communication Efficient Federated Kernel $k$-Means
Theoretical analysis shows: 1) DSPGD with CEM converges with an $O(1/T)$ rate, where $T$ is the number of iterations; 2) the communication cost of DSPGD with CEM is unrelated to the number of data samples; 3) the clustering loss of the federated kernel $k$-means can approach that of the centralized kernel $k$-means.
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail.
Ranked #18 on
Long-tail Learning
on iNaturalist 2018
Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules.
Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets.
Contrastive Learning
Semi-Supervised Image Classification
+2
Volumetric Attention for 3D Medical Image Segmentation and Detection
A volumetric attention(VA) module for 3D medical image segmentation and detection is proposed.
Structure-Feature based Graph Self-adaptive Pooling
To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes.
Towards Universal Object Detection by Domain Attention
Experiments, on a newly established universal object detection benchmark of 11 diverse datasets, show that the proposed detector outperforms a bank of individual detectors, a multi-domain detector, and a baseline universal detector, with a 1. 3x parameter increase over a single-domain baseline detector.
Feature Space Transfer for Data Augmentation
A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose.
