Search Results for author:
Found 48 papers, 27 papers with code
ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation
We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and believable outputs and significantly outperforms existing zero-shot methods.
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training.
Unsupervised Domain Adaptation via Distilled Discriminative Clustering
Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data.
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as BERT, ViT, GPT, etc.
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
In this work, we explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field.
Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
Furthermore, we propose to leverage VisionandLanguage Pre-trained Models (VLPMs) like CLIP as the surrogate model to improve the transferability of the crafted UCs to diverse domains.
Million-scale Object Detection with Large Vision Model
Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system.
Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference
To avoid obvious stage learning bottlenecks, we propose a brand-new stage-isolation based incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task of each stage without the interference of others.
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification
Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability in real world application.
Integrally Pre-Trained Transformer Pyramid Networks
In this paper, we present an integral pre-training framework based on masked image modeling (MIM).
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.
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.
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.
Semi-supervised Crowd Counting via Density Agency
In this paper, we propose a new agency-guided semi-supervised counting approach.
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain
Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.
DAS: Densely-Anchored Sampling for Deep Metric Learning
To this end, we propose a Densely-Anchored Sampling (DAS) scheme that considers the embedding with corresponding data point as "anchor" and exploits the anchor's nearby embedding space to densely produce embeddings without data points.
Ranked #2 on
Metric Learning
on CUB-200-2011
Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval
Our goal in this research is to study a more realistic environment in which we can conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories.
Prompt-based Learning for Unpaired Image Captioning
Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL-PTMs for the UIC task.
Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification
The proposed VABPP method is the first time that the view-aware-based method is used as a post-processing method in the field of vehicle re-identification.
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.
Boost Test-Time Performance with Closed-Loop Inference
Motivated by this, we propose to predict those hard-classified test samples in a looped manner to boost the model performance.
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
For example, MPQ search on ResNet18 with our indicators takes only 0. 06 s, which improves time efficiency exponentially compared to iterative search methods.
Peng Cheng Object Detection Benchmark for Smart City
Considering the diversity and complexity of scenes in intelligent city governance, we build a large-scale object detection benchmark for the smart city.
Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition
The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e. g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN).
Boosting Crowd Counting via Multifaceted Attention
Secondly, we design the Local Attention Regularization to supervise the training of LRA by minimizing the deviation among the attention for different feature locations.
Conceptor Learning for Class Activation Mapping
Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs).
Towards End-to-End Image Compression and Analysis with Transformers
Meanwhile, we propose a feature aggregation module to fuse the compressed features with the selected intermediate features of the Transformer, and feed the aggregated features to a deconvolutional neural network for image reconstruction.
Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection
In the second stage, augmented source and target data with pseudo labels are adopted to perform the self-training for prediction consistency.
Learning to Share in Multi-Agent Reinforcement Learning
Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neighbors so as to encourage agents to cooperate on the global objective through collectives.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
An Informative Tracking Benchmark
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming.
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).
M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining
Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the lack of large-scale modality-diverse datasets.
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.
Direct Measure Matching for Crowd Counting
Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
Self-Supervised Tracking via Target-Aware Data Synthesis
While deep-learning based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training.
Learning Scalable lY=-Constrained Near-Lossless Image Compression via Joint Lossy Image and Residual Compression
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
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.
Conformer: Local Features Coupling Global Representations for Visual Recognition
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.
Ranked #278 on
Image Classification
on ImageNet
Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings
Recent efforts towards video anomaly detection (VAD) try to learn a deep autoencoder to describe normal event patterns with small reconstruction errors.
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 (Zero-Shot)
on CMRC 2018
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+18
AAformer: Auto-Aligned Transformer for Person Re-Identification
In this paper, we introduce an alignment scheme in Transformer architecture for the first time and propose the Auto-Aligned Transformer (AAformer) to automatically locate both the human parts and non-human ones at patch-level.
Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
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 #1 on
Visual Object Tracking
on TNL2K
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.
Contrastive Neural Architecture Search with Neural Architecture Comparators
One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures.
Classification of Single-View Object Point Clouds
By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.
Modular Graph Attention Network for Complex Visual Relational Reasoning
Moreover, to capture the complex logic in a query, we construct a relational graph to represent the visual objects and their relationships, and propose a multi-step reasoning method to progressively understand the complex logic.
Ranked #2 on
Referring Expression Comprehension
on CLEVR-Ref+
