Search Results for author:
Found 34 papers, 23 papers with code
MuseumMaker: Continual Style Customization without Catastrophic Forgetting
However, catastrophic forgetting issue make it hard to continually synthesize new user-provided styles while retaining the satisfying results amongst learned styles.
SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
Recent advancements in the vision-language model have shown notable generalization in vision-language tasks after visual instruction tuning.
Ranked #38 on
Visual Question Answering
on MM-Vet
M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Tracking
3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving.
Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
This approach can serve as a plug-and-play data generation and augmentation module for existing camouflaged object detection tasks and provides a novel way to introduce more diversity and distributions into current camouflage datasets.
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
In summary, an OV method learns task-specific information using strong supervision from base annotations and novel category information using weak supervision from image-captions pairs.
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
Image as Set of Points
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
Making Reconstruction-based Method Great Again for Video Anomaly Detection
With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3].
A Close Look at Spatial Modeling: From Attention to Convolution
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism.
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively.
Ranked #4 on
Point Cloud Segmentation
on PointCloud-C
Semi-supervised Domain Adaptive Structure Learning
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation
For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features.
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity.
SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.
The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces
Recognizing Families In the Wild (RFIW), held as a data challenge in conjunction with the 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG), is a large-scale, multi-track visual kinship recognition evaluation.
Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective
Several recent works questioned the value of inheriting weight in structured neural network pruning because they empirically found training from scratch can match or even outperform finetuning a pruned model.
MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning
In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning.
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
Specifically, for the layers connected by the same residual, we select the filters of the same indices as unimportant filters.
Rethinking Adam: A Twofold Exponential Moving Average Approach
The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.
Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
This paper is meant to explain it through the lens of dynamical isometry [42].
Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
This scheme boosts the average performance and preserves identity information while removing demographic knowledge.
Recent Advances on Neural Network Pruning at Initialization
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network.
Context Reasoning Attention Network for Image Super-Resolution
However, the basic convolutional layer in CNNs is designed to extract local patterns, lacking the ability to model global context.
Aspect-based Sentiment Classification via Reinforcement Learning
As texts always contain a large proportion of task-irrelevant words, accurate alignment between aspects and their sentimental descriptions is the most crucial and challenging step.
Neural Pruning via Growing Regularization
Regularization has long been utilized to learn sparsity in deep neural network pruning.
SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
Even as impressive milestones are achieved in synthesizing faces, the importance of preserving identity is needed in practice and should not be overlooked.
Face Recognition: Too Bias, or Not Too Bias?
Thus, the conventional approach of learning a global threshold for all pairs resulting in performance gaps among subgroups.
Contradictory Structure Learning for Semi-supervised Domain Adaptation
Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain.
Self-Directed Online Machine Learning for Topology Optimization
A small number of training data is generated dynamically based on the DNN's prediction of the optimum.
PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment.
Ranked #1 on
Unsupervised Domain Adaptation
on PreSIL to KITTI
