Search Results for author:
Found 36 papers, 25 papers with code
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
Human beings can leverage knowledge from relative tasks to improve learning on a primary task.
Generative Inbetweening through Frame-wise Conditions-Driven Video Generation
Generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input.
$S^3$: Synonymous Semantic Space for Improving Zero-Shot Generalization of Vision-Language Models
Recently, many studies have been conducted to enhance the zero-shot generalization ability of vision-language models (e. g., CLIP) by addressing the semantic misalignment between image and text embeddings in downstream tasks.
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
To effectively and efficiently explore the potential of pre-trained models in transferring to target domain, our TAMT proposes a Hierarchical Temporal Tuning Network (HTTN), whose core involves local temporal-aware adapters (TAA) and a global temporal-aware moment tuning (GTMT).
Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark
The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of foreground objects.
Conditional Controllable Image Fusion
To address this issue, we propose a conditional controllable fusion (CCF) framework for general image fusion tasks without specific training.
Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation
Our findings suggest that prioritizing the synthesis of easier samples from the original dataset can enhance the quality of distilled datasets, especially in low IPC (image-per-class) settings.
SelfDRSC++: Self-Supervised Learning for Dual Reversed Rolling Shutter Correction
Subsequently, to effectively train the DRSC network, we propose a self-supervised learning strategy that ensures cycle consistency between input and reconstructed dual reversed RS images.
Fine-Grained Domain Generalization with Feature Structuralization
Likewise, we propose a Feature Structuralized Domain Generalization (FSDG) model, wherein features experience structuralization into common, specific, and confounding segments, harmoniously aligned with their relevant semantic concepts, to elevate performance in FGDG.
AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
To this end, we disassemble three key components involved in computation of logit bias (i. e., logit features, logit predictor, and logit fusion) and empirically analyze the effect on performance of few-shot classification.
A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences.
Tuning Pre-trained Model via Moment Probing
Distinguished from LP which builds a linear classification head based on the mean of final features (e. g., word tokens for ViT) or classification tokens, our MP performs a linear classifier on feature distribution, which provides the stronger representation ability by exploiting richer statistical information inherent in features.
DropCov: A Simple yet Effective Method for Improving Deep Architectures
Particularly, we for the first time show that \textit{effective post-normalization can make a good trade-off between representation decorrelation and information preservation for GCP, which are crucial to alleviate over-fitting and increase representation ability of deep GCP networks, respectively}.
Reliable and Interpretable Personalized Federated Learning
When there are large differences in data distribution among clients, it is crucial for federated learning to design a reliable client selection strategy and an interpretable client communication framework to better utilize group knowledge.
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
Few-shot classification is a challenging problem as only very few training examples are given for each new task.
Temporal-attentive Covariance Pooling Networks for Video Recognition
Then, a temporal covariance pooling performs temporal pooling of the attentive covariance representations to characterize both intra-frame correlations and inter-frame cross-correlations of the calibrated features.
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset.
Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33, 600 HD frames in various scenarios.
So-ViT: Mind Visual Tokens for Vision Transformer
Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification.
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude.
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity.
Ranked #5 on
Object Detection
on PKU-DDD17-Car
Neural Blind Deconvolution Using Deep Priors
To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution.
Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance.
Deep Global Generalized Gaussian Networks
To handle this issue, this paper proposes a novel deep global generalized Gaussian network (3G-Net), whose core is to estimate a global covariance of generalized Gaussian for modeling the last convolutional activations.
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
The proposed methods are highly modular, readily plugged into existing deep CNNs.
Ranked #1 on
Image Classification
on iNaturalist
(Top 3 Error metric)
Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks
However, both GAP and existing HOP methods assume unimodal distributions, which cannot fully capture statistics of convolutional activations, limiting representation ability of deep CNNs, especially for samples with complex contents.
Global Second-order Pooling Convolutional Networks
Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks.
Multi-scale Location-aware Kernel Representation for Object Detection
Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation. Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection.
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
Towards addressing this problem, we propose an iterative matrix square root normalization method for fast end-to-end training of global covariance pooling networks.
Ranked #14 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Image Recognition
G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition
Recently, plugging trainable structural layers into deep convolutional neural networks (CNNs) as image representations has made promising progress.
Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable.
Is Second-order Information Helpful for Large-scale Visual Recognition?
The main challenges involved are robust covariance estimation given a small sample of large-dimensional features and usage of the manifold structure of covariance matrices.
RAID-G: Robust Estimation of Approximate Infinite Dimensional Gaussian With Application to Material Recognition
Infinite dimensional covariance descriptors can provide richer and more discriminative information than their low dimensional counterparts.
Towards Effective Codebookless Model for Image Classification
The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade.
From Dictionary of Visual Words to Subspaces: Locality-Constrained Affine Subspace Coding
The locality-constrained linear coding (LLC) is a very successful feature coding method in image classification.
