Search Results for author:
Found 36 papers, 21 papers with code
Rethinking Optimization and Architecture for Tiny Language Models
Several design formulas are empirically proved especially effective for tiny language models, including tokenizer compression, architecture tweaking, parameter inheritance and multiple-round training.
Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models
Recent advancements in Multi-modality Large Language Models (MLLMs) have demonstrated remarkable capabilities in complex high-level vision tasks.
A Theory of Non-Acyclic Generative Flow Networks
GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward.
Exploring the Naturalness of AI-Generated Images
In this paper, we take the first step to benchmark and assess the visual naturalness of AI-generated images.
Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering
We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity.
Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping
We present a simple yet novel parameterized form of linear mapping to achieves remarkable network compression performance: a pseudo SVD called Ternary SVD (TSVD).
Reparameterization through Spatial Gradient Scaling
Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training.
A General-Purpose Transferable Predictor for Neural Architecture Search
In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators.
AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
Evaluating neural network performance is critical to deep neural network design but a costly procedure.
GENNAPE: Towards Generalized Neural Architecture Performance Estimators
In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble.
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Lifelong object re-identification incrementally learns from a stream of re-identification tasks.
OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source and target domains.
R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning
Systematicity, i. e., the ability to recombine known parts and rules to form new sequences while reasoning over relational data, is critical to machine intelligence.
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency.
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
We propose an approach to IML, which we call Episodic Replay Distillation (ERD), that mixes classes from the current task with class exemplars from previous tasks when sampling episodes for meta-learning.
Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization
Anderson mixing has been heuristically applied to reinforcement learning (RL) algorithms for accelerating convergence and improving the sampling efficiency of deep RL.
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data.
Ranked #3 on
Source-Free Domain Adaptation
on VisDA-2017
Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
Distributional Reinforcement Learning
reinforcement-learning
+1
A Transferable General-Purpose Predictor for Neural Architecture Search
Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS).
Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data
Therefore, we investigate knowledge distillation to transfer knowledge from a high-quality unconditioned generative model (e. g., StyleGAN) to a conditioned synthetic image generation modules in a variety of systems.
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search
Neural architecture search automates neural network design and has achieved state-of-the-art results in many deep learning applications.
L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning
In this paper, we propose L$^{2}$NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the distribution of high-performing architectures in the search history.
Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
Generalized Source-free Domain Adaptation
In this paper, we propose a new domain adaptation paradigm called Generalized Source-free Domain Adaptation (G-SFDA), where the learned model needs to perform well on both the target and source domains, with only access to current unlabeled target data during adaptation.
Ranked #2 on
Source-Free Domain Adaptation
on VisDA-2017
ReNAS: Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
Generative Adversarial Neural Architecture Search
Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess.
MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains
Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs.
Generative Adversarial Neural Architecture Search with Importance Sampling
Despite the empirical success of neural architecture search (NAS) algorithms in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to be assessed.
Casting a BAIT for Offline and Online Source-free Domain Adaptation
When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Neural Architecture Search For Keyword Spotting
Deep neural networks have recently become a popular solution to keyword spotting systems, which enable the control of smart devices via voice.
Ranked #1 on
Keyword Spotting
on Google Speech Commands
(Google Speech Commands V1 6 metric)
Generative Feature Replay For Class-Incremental Learning
To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
ReNAS:Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
Three-Head Neural Network Architecture for AlphaZero Learning
A three-head network architecture has been recently proposed that can learn a third action-value head on a fixed dataset the same as for two-head net.
Deep Demosaicing for Edge Implementation
We provide an exhaustive search of deep neural network architectures and obtain a pareto front of Color Peak Signal to Noise Ratio (CPSNR) as the performance criterion versus the number of parameters as the model complexity that beats the state-of-the-art.
Single-step Options for Adversary Driving
In this paper, we use reinforcement learning for safety driving in adversary settings.
