Search Results for author:
Found 168 papers, 90 papers with code
Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning
Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems.
Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
The LER optimizes the distribution of potential known class samples in unlabeled data, thus ensuring the preservation of knowledge related to known categories while learning novel classes.
Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generation
X-ray image based medical report generation achieves significant progress in recent years with the help of the large language model, however, these models have not fully exploited the effective information in visual image regions, resulting in reports that are linguistically sound but insufficient in describing key diseases.
AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene
Compared to frame-based methods, computational neuromorphic imaging using event cameras offers significant advantages, such as minimal motion blur, enhanced temporal resolution, and high dynamic range.
VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition
Inspired by the successful application of large models, the introduction of such large models can also be considered to further enhance the performance of multi-modal tasks.
RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing
The core of RoomPainter features a zero-shot technique that effectively adapts a 2D diffusion model for 3D-consistent texture synthesis, along with a two-stage generation strategy that ensures both global and local consistency.
High-speed and High-quality Vision Reconstruction of Spike Camera with Spike Stability Theorem
To realize high-speed and high-quality vision reconstruction of the spike camera, we propose a new spike stability theorem that reveals the relationship between spike stream characteristics and stable light intensity.
Flexible and Scalable Deep Dendritic Spiking Neural Networks with Multiple Nonlinear Branching
Our work firstly demonstrates the possibility of training bio-plausible dendritic SNNs with depths and scales comparable to traditional point SNNs, and reveals superior expressivity and robustness of reduced dendritic neuron models in deep learning, thereby offering a fresh perspective on advancing neural network design.
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
Object detection in event streams has emerged as a cutting-edge research area, demonstrating superior performance in low-light conditions, scenarios with motion blur, and rapid movements.
Core Placement Optimization of Many-core Brain-Inspired Near-Storage Systems for Spiking Neural Network Training
In order to improve the computing parallelism and system throughput of the many-core near-memory computing system, and to reduce power consumption, we propose a SNN training many-core deployment optimization method based on Off-policy Deterministic Actor-Critic.
Open-Sora Plan: Open-Source Large Video Generation Model
We introduce Open-Sora Plan, an open-source project that aims to contribute a large generation model for generating desired high-resolution videos with long durations based on various user inputs.
HDI-Former: Hybrid Dynamic Interaction ANN-SNN Transformer for Object Detection Using Frames and Events
To address these challenges, we propose HDI-Former, a Hybrid Dynamic Interaction ANN-SNN Transformer, marking the first trial to design a directly trained hybrid ANN-SNN architecture for high-accuracy and energy-efficient object detection using frames and events.
A High Energy-Efficiency Multi-core Neuromorphic Architecture for Deep SNN Training
There is a growing necessity for edge training to adapt to dynamically changing environment.
Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body
Intuitively, Visual Language Models (VLMs) that have obtained remarkable performance on various visual tasks are quite suitable for this task.
ETTFS: An Efficient Training Framework for Time-to-First-Spike Neuron
Spiking Neural Networks (SNNs) have attracted considerable attention due to their biologically inspired, event-driven nature, making them highly suitable for neuromorphic hardware.
Spatial-Temporal Search for Spiking Neural Networks
Drawing inspiration from the heterogeneity of biological neural networks, we propose a differentiable approach to optimize SNN on both spatial and temporal dimensions.
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection
We propose a novel method utilizing attributes in vision-language foundation models for incremental object detection.
Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation
Under this unified framework, the proposed method can progressively and explicitly transfer knowledge from clean scenes to real adverse weather.
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
In this paper, we propose a large-scale, high-definition ($1280 \times 800$) human action recognition dataset based on the CeleX-V event camera, termed CeleX-HAR.
Time-Dependent VAE for Building Latent Representations from Visual Neural Activity with Complex Dynamics
Seeking high-quality representations with latent variable models (LVMs) to reveal the intrinsic correlation between neural activity and behavior or sensory stimuli has attracted much interest.
HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry.
Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion
FFM is designed for the fusion of contextual information within neighboring event streams, leveraging the coupling relationship between positive and negative events to alleviate the misleading of noises in the respective branches.
Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition
In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++.
SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition
To address this challenge, some researchers have turned to brain-inspired spiking neural networks (SNNs), such as recurrent SNNs and ANN-converted SNNs, leveraging their inherent temporal dynamics and energy efficiency.
EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
Capitalizing on the high temporal resolution and dynamic range offered by the event camera, we leverage the event streams to explicitly model the formation process of motion-blurred images and guide the deblurring reconstruction of 3D-GS.
High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost
This work is expected to break the technical bottleneck of significantly increasing memory cost and training time for large-scale SNNs while maintaining high performance and low inference energy cost.
Sensitivity Decouple Learning for Image Compression Artifacts Reduction
Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, ie, the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree.
Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods
In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance in a systematic and comprehensive way, including theory fundamentals, spiking neuron models, advanced SNN models and residual architectures, software frameworks and neuromorphic hardware, applications, and future trends.
Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition
Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features.
State Space Model for New-Generation Network Alternative to Transformers: A Survey
In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM.
MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control
Traffic signal control has a great impact on alleviating traffic congestion in modern cities.
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
ii) We incorporate the hierarchical structure, which significantly benefits the performance of both the brain and artificial neural networks, into spiking transformers to obtain multi-scale spiking representation.
Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline
Current event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios remains unclear.
Noisy Spiking Actor Network for Exploration
As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies.
Adaptive Discovering and Merging for Incremental Novel Class Discovery
One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner.
Optimal ANN-SNN Conversion with Group Neurons
For instance, while converting artificial neural networks (ANNs) to SNNs circumvents the need for direct training of SNNs, it encounters issues related to conversion errors and high inference time delays.
Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
CNN-based SNNs are the current mainstream of neuromorphic computing.
Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning
Recently, the surrogate gradient method has been utilized for training multi-layer SNNs, which allows SNNs to achieve comparable performance with the corresponding deep networks in this task.
CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras
In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras.
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket
To the best of our knowledge, this is the first time that the SNN achieves 80+% accuracy on ImageNet.
DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
We explore visual reinforcement learning (RL) using two complementary visual modalities: frame-based RGB camera and event-based Dynamic Vision Sensor (DVS).
Event-based Visible and Infrared Fusion via Multi-task Collaboration
Visible and Infrared image Fusion (VIF) offers a comprehensive scene description by combining thermal infrared images with the rich textures from visible cameras.
Machine Mindset: An MBTI Exploration of Large Language Models
We present a novel approach for integrating Myers-Briggs Type Indicator (MBTI) personality traits into large language models (LLMs), addressing the challenges of personality consistency in personalized AI.
Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition
It is intuitive to combine them for high-performance RGB-Event based video recognition, however, existing works fail to achieve a good balance between the accuracy and model parameters, as shown in Fig.~\ref{firstimage}.
SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties.
HiFi-123: Towards High-fidelity One Image to 3D Content Generation
Our contributions are twofold: First, we propose a Reference-Guided Novel View Enhancement (RGNV) technique that significantly improves the fidelity of diffusion-based zero-shot novel view synthesis methods.
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline
Tracking using bio-inspired event cameras has drawn more and more attention in recent years.
Knowledge Prompt-tuning for Sequential Recommendation
Pre-trained language models (PLMs) have demonstrated strong performance in sequential recommendation (SR), which are utilized to extract general knowledge.
SODFormer: Streaming Object Detection with Transformer Using Events and Frames
Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance.
SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition
Secondly, they adopt either Spiking Neural Networks (SNN) for energy-efficient recognition with suboptimal results, or Artificial Neural Networks (ANN) for energy-intensive, high-performance recognition.
Learning Sparse Neural Networks with Identity Layers
Applying such theory, we propose a plug-and-play CKA-based Sparsity Regularization for sparse network training, dubbed CKA-SR, which utilizes CKA to reduce feature similarity between layers and increase network sparsity.
Spike-driven Transformer
In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: 1) Event-driven, no calculation is triggered when the input of Transformer is zero; 2) Binary spike communication, all matrix multiplications associated with the spike matrix can be transformed into sparse additions; 3) Self-attention with linear complexity at both token and channel dimensions; 4) The operations between spike-form Query, Key, and Value are mask and addition.
Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model
AI legal assistants based on Large Language Models (LLMs) can provide accessible legal consulting services, but the hallucination problem poses potential legal risks.
Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains, which are usually infeasible for realistic applications.
Spatial Re-parameterization for N:M Sparsity
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity in CNNs.
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification
Extensive experiments demonstrate that (1) CRS approximately measures the performance of models without labeled samples; (2) and PEG produces new state-of-the-art accuracy for person re-identification, indicating the great potential of population-based network cooperative training for unsupervised learning.
Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition
To address these issues, we propose a novel dual point-voxel absorbing graph representation learning for event stream data representation.
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
We further conduct experiments to quantify how temporal structures (dynamic information) and static textures (static information) of the movie stimuli influence representational similarity, suggesting that our model benefits from long-range feedback to encode context-dependent representations just like the brain.
Auto-Spikformer: Spikformer Architecture Search
The integration of self-attention mechanisms into Spiking Neural Networks (SNNs) has garnered considerable interest in the realm of advanced deep learning, primarily due to their biological properties.
Temporal Contrastive Learning for Spiking Neural Networks
However, in this work, we find the method above is not ideal for the SNNs training as it omits the temporal dynamics of SNNs and degrades the performance quickly with the decrease of inference time steps.
Album Storytelling with Iterative Story-aware Captioning and Large Language Models
One natural approach is to use caption models to describe each photo in the album, and then use LLMs to summarize and rewrite the generated captions into an engaging story.
Probabilistic Modeling: Proving the Lottery Ticket Hypothesis in Spiking Neural Network
LTH opens up a new path for network pruning.
Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation
In this paper, we propose ConvBN-MaxPooling-LIF (CML), an SNN-optimized downsampling with precise gradient backpropagation.
Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
Vanilla spiking neurons in Spiking Neural Networks (SNNs) use charge-fire-reset neuronal dynamics, which can only be simulated serially and can hardly learn long-time dependencies.
Spikingformer: Spike-driven Residual Learning for Transformer-based Spiking Neural Network
Based on this residual design, we develop Spikingformer, a pure transformer-based spiking neural network.
Picking Up Quantization Steps for Compressed Image Classification
The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file.
Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning
However, in this work, we find that the CE loss is not ideal for the base session training as it suffers poor class separation in terms of representations, which further degrades generalization to novel classes.
Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mouse
However, they highly simplify the computational properties of neurons compared to their biological counterparts.
A Unified Framework for Soft Threshold Pruning
In this work, we reformulate soft threshold pruning as an implicit optimization problem solved using the Iterative Shrinkage-Thresholding Algorithm (ISTA), a classic method from the fields of sparse recovery and compressed sensing.
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
We also give visualization and analysis of the model parameters and results on representative downstream tasks.
Training Full Spike Neural Networks via Auxiliary Accumulation Pathway
The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN.
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation
Unsupervised domain adaption has been widely adopted in tasks with scarce annotated data.
Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning
Efficient motion and appearance modeling are critical for vision-based Reinforcement Learning (RL).
Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation
Vision-based reinforcement learning (RL) depends on discriminative representation encoders to abstract the observation states.
Part-guided Relational Transformers for Fine-grained Visual Recognition
This framework, namely PArt-guided Relational Transformers (PART), is proposed to learn the discriminative part features with an automatic part discovery module, and to explore the intrinsic correlations with a feature transformation module by adapting the Transformer models from the field of natural language processing.
Ranked #8 on
Fine-Grained Image Classification
on FGVC Aircraft
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+1
Parsing Objects at a Finer Granularity: A Survey
Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e. g., agriculture, remote sensing, and space technologies.
Universal Object Detection with Large Vision Model
In this study, our focus is on a specific challenge: the large-scale, multi-domain universal object detection problem, which contributes to the broader goal of achieving a universal vision system.
Shadow Removal by High-Quality Shadow Synthesis
Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image.
Event-based Monocular Dense Depth Estimation with Recurrent Transformers
Event cameras, offering high temporal resolutions and high dynamic ranges, have brought a new perspective to address common challenges (e. g., motion blur and low light) in monocular depth estimation.
Meta Architecture for Point Cloud Analysis
However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field.
Ranked #2 on
3D Semantic Segmentation
on OpenTrench3D
Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric
In this paper, we propose a single-stage backbone network for Color-Event Unified Tracking (CEUTrack), which achieves the above functions simultaneously.
Ranked #3 on
Object Tracking
on COESOT
HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption.
Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
In addition, considering that the existing real rain datasets are of low quality, either small scale or downloaded from the internet, we collect a real large-scale dataset under various rainy kinds of weather that contains high-resolution rainy images.
Spikformer: When Spiking Neural Network Meets Transformer
Spikformer (66. 3M parameters) with comparable size to SEW-ResNet-152 (60. 2M, 69. 26%) can achieve 74. 81% top1 accuracy on ImageNet using 4 time steps, which is the state-of-the-art in directly trained SNNs models.
Attention Spiking Neural Networks
On ImageNet-1K, we achieve top-1 accuracy of 75. 92% and 77. 08% on single/4-step Res-SNN-104, which are state-of-the-art results in SNNs.
Fine-Grained Object Classification via Self-Supervised Pose Alignment
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods.
Training-free Transformer Architecture Search
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
Ranked #2 on
Point Cloud Segmentation
on PointCloud-C
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+2
Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection
To solve this problem, we propose the Annotation Efficient Person Re-Identification method to select image pairs from an alternative pair set according to the fallibility and diversity of pairs, and train the Re-ID model based on the annotation.
Transformations in Learned Image Compression from a Modulation Perspective
In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation.
Event-based Video Reconstruction via Potential-assisted Spiking Neural Network
We propose a novel Event-based Video reconstruction framework based on a fully Spiking Neural Network (EVSNN), which utilizes Leaky-Integrate-and-Fire (LIF) neuron and Membrane Potential (MP) neuron.
Computational Efficiency
Event-Based Video Reconstruction
+2
PowerGear: Early-Stage Power Estimation in FPGA HLS via Heterogeneous Edge-Centric GNNs
Specifically, in the graph construction flow, we introduce buffer insertion, datapath merging, graph trimming and feature annotation techniques to transform HLS designs into graph-structured data, which encode both intra-operation micro-architectures and inter-operation interconnects annotated with switching activities.
1000x Faster Camera and Machine Vision with Ordinary Devices
By treating vidar as spike trains in biological vision, we have further developed a spiking neural network-based machine vision system that combines the speed of the machine and the mechanism of biological vision, achieving high-speed object detection and tracking 1, 000x faster than human vision.
Deep Reinforcement Learning with Spiking Q-learning
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption.
Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
PSNR-oriented models are a critical class of super-resolution models with applications across various fields.
Neural Architecture Search With Representation Mutual Information
Building upon RMI, we further propose a new search algorithm termed RMI-NAS, facilitating with a theorem to guarantee the global optimal of the searched architecture.
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
Optimized Separable Convolution: Yet Another Efficient Convolution Operator
In this research, we propose a novel and principled operator called optimized separable convolution by optimal design for the internal number of groups and kernel sizes for general separable convolutions can achieve the complexity of O(C^{\frac{3}{2}}K).
Heterogeneous Relational Complement for Vehicle Re-identification
The crucial problem in vehicle re-identification is to find the same vehicle identity when reviewing this object from cross-view cameras, which sets a higher demand for learning viewpoint-invariant representations.
An Information Theory-inspired Strategy for Automatic Network Pruning
This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.
Ranked #7 on
Out-of-Distribution Detection
on CIFAR-10
VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.
Ranked #1 on
Object Tracking
on VisEvent
MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking
The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively.
Ranked #37 on
Rgb-T Tracking
on RGBT234
High-Speed Image Reconstruction Through Short-Term Plasticity for Spiking Cameras
Mimicking the sampling mechanism of the fovea, a retina-inspired camera, named spiking camera, is developed to record the external information with a sampling rate of 40, 000 Hz, and outputs asynchronous binary spike streams.
Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking.
1xN Pattern for Pruning Convolutional Neural Networks
We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations.
Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks
We show that the inference time can be reduced by optimizing the upper bound of the fit curve in the revised ANN to achieve fast inference.
Pruning of Deep Spiking Neural Networks through Gradient Rewiring
Our key innovation is to redefine the gradient to a new synaptic parameter, allowing better exploration of network structures by taking full advantage of the competition between pruning and regrowth of connections.
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (One-Shot)
on DuReader
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+19
Carrying out CNN Channel Pruning in a White Box
Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
We believe this benchmark will greatly boost related researches on natural language guided tracking.
Ranked #6 on
Visual Object Tracking
on TNL2K
(precision metric)
Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy.
Distilling a Powerful Student Model via Online Knowledge Distillation
Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one.
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Adversarial Reciprocal Points Learning for Open Set Recognition
Then, an adversarial margin constraint is proposed to reduce the open space risk by limiting the latent open space constructed by reciprocal points.
Collaborative Intelligence: Challenges and Opportunities
This paper presents an overview of the emerging area of collaborative intelligence (CI).
Deep Residual Learning in Spiking Neural Networks
Previous Spiking ResNet mimics the standard residual block in ANNs and simply replaces ReLU activation layers with spiking neurons, which suffers the degradation problem and can hardly implement residual learning.
MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control
To make the policy learned from a training scenario generalizable to new unseen scenarios, a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method is proposed to learn the decentralized policy for each intersection that considers neighbor information in a latent way.
Rethinking Convolution: Towards an Optimal Efficiency
In this research, we propose a novel operator called \emph{optimal separable convolution} which can be calculated at $O(C^{\frac{3}{2}}KHW)$ by optimal design for the internal number of groups and kernel sizes for general separable convolutions.
NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras
In this paper, we propose a NeuSpike-Net to learn both the high dynamic range and high motion sensitivity of DVS and the full texture sampling of spike camera to achieve high-speed and high dynamic image reconstruction.
Fast Class-wise Updating for Online Hashing
To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.
Annotation-Efficient Untrimmed Video Action Recognition
In this paper, we target a new problem, Annotation-Efficient Video Recognition, to reduce the requirement of annotations for both large amount of samples and the action location.
Learning Open Set Network with Discriminative Reciprocal Points
In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data.
Masked Face Recognition with Latent Part Detection
The proposed LPD model is trained in an end-to-end manner and only utilizes the original and synthetic training data.
Intrinsic Relationship Reasoning for Small Object Detection
In this paper, we propose a novel context reasoning approach for small object detection which models and infers the intrinsic semantic and spatial layout relationships between objects.
Cooperative Bi-path Metric for Few-shot Learning
Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples.
Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
To solve this problem, cross-domain FSL (CDFSL) is proposed very recently to transfer knowledge from general-domain base classes to special-domain novel classes.
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks
In this paper, we take inspiration from the observation that membrane-related parameters are different across brain regions, and propose a training algorithm that is capable of learning not only the synaptic weights but also the membrane time constants of SNNs.
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored.
Domain Adaptive Person Re-Identification
Ensemble Learning
+1
SEKD: Self-Evolving Keypoint Detection and Description
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks.
Rethinking Performance Estimation in Neural Architecture Search
In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space.
Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature representation composed of important primitives, which is jointly trained with two parts, i. e. primitive discovery and primitive enhancing.
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown.
Ranked #9 on
Unsupervised Domain Adaptation
on Duke to Market
Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
In this work, we propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains while considering the instantaneous alignment difficulty.
HRank: Filter Pruning using High-Rank Feature Map
The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.
Filter Sketch for Network Pruning
Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure.
Channel Pruning via Automatic Structure Search
In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i. e., channel number in each layer, rather than selecting "important" channels as previous works did.
Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
Through these two attentions, we use the Purificatory Mechanism to impose strict weights with different regions of the whole salient objects and purify results from hard-to-distinguish regions, thus accurately predicting the locations and details of salient objects.
