Search Results for author:
Found 26 papers, 20 papers with code
Transferable and Principled Efficiency for Open-Vocabulary Segmentation
In the context of efficient OVS, we target achieving performance that is comparable to or even better than prior OVS works based on large vision-language foundation models, by utilizing smaller models that incur lower training costs.
Principled Architecture-aware Scaling of Hyperparameters
However, most designs or optimization methods are agnostic to the choice of network structures, and thus largely ignore the impact of neural architectures on hyperparameters.
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
To reduce the need for training data with simulated solutions, we pretrain neural operators on unlabeled PDE data using reconstruction-based proxy tasks.
Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost.
Lifelong Language Pretraining with Distribution-Specialized Experts
Compared to existing lifelong learning approaches, Lifelong-MoE achieves better few-shot performance on 19 downstream NLP tasks.
Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
In this paper, we propose a data-model-hardware tri-design framework for high-throughput, low-cost, and high-accuracy multi-object tracking (MOT) on High-Definition (HD) video stream.
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex.
Auto-scaling Vision Transformers without Training
The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart.
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining
Conventional methods often require (iterative) pruning followed by re-training, which not only incurs large overhead beyond the original DNN training but also can be sensitive to retraining hyperparameters.
Font Completion and Manipulation by Cycling Between Multi-Modality Representations
The novel graph constructor maps a glyph's latent code to its graph representation that matches expert knowledge, which is trained to help the translation task.
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
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.
DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference
Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms.
Contrastive Syn-to-Real Generalization
Training on synthetic data can be beneficial for label or data-scarce scenarios.
Learning to Optimize: A Primer and A Benchmark
It automates the design of an optimization method based on its performance on a set of training problems.
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost?
Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity
We present Sandwich Batch Normalization (SaBN), a frustratingly easy improvement of Batch Normalization (BN) with only a few lines of code changes.
Ranked #20 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-100
AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations.
Automated Synthetic-to-Real Generalization
Models trained on synthetic images often face degraded generalization to real data.
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i. e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples.
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression and develop an AutoGAN-Distiller (AGD) framework.
FasterSeg: Searching for Faster Real-time Semantic Segmentation
We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods.
Ranked #1 on
Semantic Segmentation
on BDD
Neural Architecture Search
Real-Time Semantic Segmentation
+1
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels.
Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification
Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification.
ABD-Net: Attentive but Diverse Person Re-Identification
Attention mechanism has been shown to be effective for person re-identification (Re-ID).
Ranked #16 on
Person Re-Identification
on Market-1501-C
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy.
Ranked #4 on
Land Cover Classification
on DeepGlobe
