Search Results for author:
Found 66 papers, 37 papers with code
Vision Transformer with Deformable Attention
On the one hand, using dense attention e. g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests.
Ranked #96 on
Object Detection
on COCO test-dev
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention
On the one hand, using dense attention in ViT leads to excessive memory and computational cost, and features can be influenced by irrelevant parts that are beyond the region of interests.
Ranked #4 on
Object Detection
on COCO 2017
Implicit Semantic Data Augmentation for Deep Networks
Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., adding sunglasses or changing backgrounds.
Regularizing Deep Networks with Semantic Data Augmentation
The proposed method is inspired by the intriguing property that deep networks are effective in learning linearized features, i. e., certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., changing the background or view angle of an object.
On the Integration of Self-Attention and Convolution
In this paper, we show that there exists a strong underlying relation between them, in the sense that the bulk of computations of these two paradigms are in fact done with the same operation.
Agent Attention: On the Integration of Softmax and Linear Attention
Specifically, the Agent Attention, denoted as a quadruple $(Q, A, K, V)$, introduces an additional set of agent tokens $A$ into the conventional attention module.
FLatten Transformer: Vision Transformer using Focused Linear Attention
The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks.
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
Specifically, we introduce Step-wise Variation Regularization to enforce the proportion between the variations of an arbitrary input latent and that of the output image is a constant at any diffusion training step.
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
Inspired by this phenomenon, we propose a Dynamic Transformer to automatically configure a proper number of tokens for each input image.
Ranked #29 on
Image Classification
on CIFAR-100
(using extra training data)
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images.
Glance and Focus Networks for Dynamic Visual Recognition
Spatial redundancy widely exists in visual recognition tasks, i. e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand.
3D Object Detection with Pointformer
In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively.
Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts.
Resolution Adaptive Networks for Efficient Inference
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks.
Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
Our method leverages an off-the-shelf object detector to identify visual objects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module.
Adaptive Focus for Efficient Video Recognition
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency.
Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint.
ActiveNeRF: Learning where to See with Uncertainty Estimation
In this paper, we present a novel learning framework, ActiveNeRF, aiming to model a 3D scene with a constrained input budget.
Adaptive Rotated Convolution for Rotated Object Detection
In our ARC module, the convolution kernels rotate adaptively to extract object features with varying orientations in different images, and an efficient conditional computation mechanism is introduced to accommodate the large orientation variations of objects within an image.
Ranked #3 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency.
Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain.
Domain Adaptation via Prompt Learning
Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given.
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
It is also effective for self-supervised learning (e. g., MAE).
Cross-Modal Adapter for Text-Video Retrieval
However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting.
Dynamic Perceiver for Efficient Visual Recognition
Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features.
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning.
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL
We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL.
Latency-aware Spatial-wise Dynamic Networks
The latency prediction model can efficiently estimate the inference latency of dynamic networks by simultaneously considering algorithms, scheduling strategies, and hardware properties.
Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks.
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
These methods appear to be quite different in the designed loss functions from various motivations.
Learning to Weight Samples for Dynamic Early-exiting Networks
Intuitively, easy samples, which generally exit early in the network during inference, should contribute more to training early classifiers.
Efficient Knowledge Distillation from Model Checkpoints
Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers).
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks.
Learning Specialized Activation Functions for Physics-informed Neural Networks
To avoid the inefficient manual selection and to alleviate the optimization difficulty of PINNs, we introduce adaptive activation functions to search for the optimal function when solving different problems.
Decoupled Prioritized Resampling for Offline RL
OPER is a plug-and-play component for offline RL algorithms.
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
To overcome this obstacle, we propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space, and samples contrastive pairs accordingly.
Ranked #8 on
Long-tail Learning
on iNaturalist 2018
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
To tackle this problem, we propose a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations.
A Reduction of the Elastic Net to Support Vector Machines with an Application to GPU Computing
Our second contribution is to derive a practical algorithm based on this reduction.
Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Different from existing policy gradient methods which employ single actor-critic but cannot realize satisfactory tracking control accuracy and stable learning, our proposed algorithm can achieve high-level tracking control accuracy of AUVs and stable learning by applying a hybrid actors-critics architecture, where multiple actors and critics are trained to learn a deterministic policy and action-value function, respectively.
Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning
Then, we present an off-policy actor-critic, model-free maximum entropy deep RL algorithm called deep soft policy gradient (DSPG) by combining soft policy gradient with soft Bellman equation.
A selected review on reinforcement learning based control for autonomous underwater vehicles
This paper provides a selected review on RL based control for AUVs with the focus on applications of RL to low-level control tasks for underwater regulation and tracking.
Robotics
Tighter Bound Estimation of Sensitivity Analysis for Incremental and Decremental Data Modification
Specifically, the proposed algorithm can be used to estimate the upper and lower bounds of the updated classifier's coefficient matrix with a low computational complexity related to the size of the updated dataset.
Smart Train Operation Algorithms based on Expert Knowledge and Reinforcement Learning
Then we develop two algorithms for optimizing the energy efficiency of train operation.
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
In this paper, we propose a novel meta-learning based SSL algorithm (Meta-Semi) that requires tuning only one additional hyper-parameter, compared with a standard supervised deep learning algorithm, to achieve competitive performance under various conditions of SSL.
Revisiting Locally Supervised Training of Deep Neural Networks
As InfoPro loss is difficult to compute in its original form, we derive a feasible upper bound as a surrogate optimization objective, yielding a simple but effective algorithm.
Robust Offline Reinforcement Learning from Low-Quality Data
We theoretically show that AdaPT produces a tight upper bound on the distributional deviation between the learned policy and the behavior policy, and this upper bound is the minimum requirement to guarantee policy improvement at each iteration.
A Unified Framework for Convolution-based Graph Neural Networks
In this paper, we take a step forward to establish a unified framework for convolution-based graph neural networks, by formulating the basic graph convolution operation as an optimization problem in the graph Fourier space.
Dynamic Neural Networks: A Survey
Dynamic neural network is an emerging research topic in deep learning.
CAM-loss: Towards Learning Spatially Discriminative Feature Representations
The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification.
Fine-Grained Few Shot Learning with Foreground Object Transformation
As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks.
Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
TSCI model builds on the formulation of temporal causality, which reflects the temporal causal relations between sequential observations and decisions of RL agent.
Learn From the Past: Experience Ensemble Knowledge Distillation
We save a moderate number of intermediate models from the training process of the teacher model uniformly, and then integrate the knowledge of these intermediate models by ensemble technique.
The Neural-Prediction based Acceleration Algorithm of Column Generation for Graph-Based Set Covering Problems
In this paper, we propose an improved column generation algorithm with neural prediction (CG-P) for solving graph-based set covering problems.
AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e. g., allocating the majority of computation to a task-relevant subset of frames or the most valuable image regions of each frame.
Contrastive Language-Image Pre-Training with Knowledge Graphs
Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising performances when transferred to downstream tasks.
Standoff Tracking Using DNN-Based MPC with Implementation on FPGA
This work studies the standoff tracking problem to drive an unmanned aerial vehicle (UAV) to slide on a desired circle over a moving target at a constant height.
Joint Representation Learning for Text and 3D Point Cloud
During the pre-training stage, we establish the correspondence of images and point clouds based on the readily available RGB-D data and use contrastive learning to align the image and point cloud representations.
Boosting Offline Reinforcement Learning with Action Preference Query
In particular, online fine-tuning has become a commonly used method to correct the erroneous estimates of out-of-distribution data learned in the offline training phase.
Computation-efficient Deep Learning for Computer Vision: A Survey
Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks.
Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation
This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments.
Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem.
GSVA: Generalized Segmentation via Multimodal Large Language Models
Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image.
Generalized Referring Expression Segmentation
Referring Expression
+1
A Reinforcement-Learning-Based Multiple-Column Selection Strategy for Column Generation
Column generation (CG) is one of the most successful approaches for solving large-scale linear programming (LP) problems.
Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
Therefore, we explore the use of image segmentation foundation models to automatically generate training labels for 3D segmentation.
LLM Agents for Psychology: A Study on Gamified Assessments
Psychological measurement is essential for mental health, self-understanding, and personal development.
Deep Reinforcement Learning for Traveling Purchaser Problems
The traveling purchaser problem (TPP) is an important combinatorial optimization problem with broad applications.
