Search Results for author:
Found 55 papers, 26 papers with code
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed with different searching directions.
A Similarity Paradigm Through Textual Regularization Without Forgetting
In this paper, we propose a novel method called Similarity Paradigm with Textual Regularization (SPTR) for prompt learning without forgetting.
HRP: High-Rank Preheating for Superior LoRA Initialization
This paper studies the crucial impact of initialization on the convergence properties of Low-Rank Adaptation (LoRA).
Detecting Discrepancies Between AI-Generated and Natural Images Using Uncertainty
In this work, we propose a novel approach for detecting AI-generated images by leveraging predictive uncertainty to mitigate misuse and associated risks.
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
Recent works propose to employ supervised fine-tuning (SFT) to mitigate the sycophancy issue, while it typically leads to the degeneration of LLMs' general capability.
Interpreting and Improving Large Language Models in Arithmetic Calculation
In this work, we delve into uncovering a specific mechanism by which LLMs execute calculations.
Advancing Prompt Learning through an External Layer
Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks.
Robust Training of Federated Models with Extremely Label Deficiency
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency.
Towards Theoretical Understandings of Self-Consuming Generative Models
This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations.
FedImpro: Measuring and Improving Client Update in Federated Learning
First, we analyze the generalization contribution of local training and conclude that this generalization contribution is bounded by the conditional Wasserstein distance between the data distribution of different clients.
Sheared Backpropagation for Fine-tuning Foundation Models
To address these challenges we introduce PreBackRazor a novel activation pruning scheme offering both computational and memory efficiency through a sparsified backpropagation strategy which judiciously avoids unnecessary activation pruning and storage and gradient computation.
Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
This limitation hinders the potential of language supervision emphasized in CLIP and restricts the learning of temporal features as the text encoder has demonstrated limited proficiency in motion understanding.
Good Questions Help Zero-Shot Image Reasoning
QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment.
Optical Quantum Sensing for Agnostic Environments via Deep Learning
DQS incorporates two essential components: a Graph Neural Network (GNN) predictor and a trigonometric interpolation algorithm.
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.
Boosting Fair Classifier Generalization through Adaptive Priority Reweighing
Our adaptive reweighing method prioritizes samples closer to the decision boundary and assigns a higher weight to improve the generalizability of fair classifiers.
Structured Cooperative Learning with Graphical Model Priors
We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical model prior to automatically coordinate mutual learning between devices.
Moderately Distributional Exploration for Domain Generalization
We show that MODE can endow models with provable generalization performance on unknown target domains.
Semantic-Aware Mixup for Domain Generalization
To mitigate the hard-fitting issue, we propose to perform a semantic-aware mixup (SAM) for domain generalization, where whether to perform mixup depends on the semantic and domain information.
On Efficient Training of Large-Scale Deep Learning Models: A Literature Review
The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech.
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
In experiments, we show that our method consistently brings non-trivial improvements to the three aforementioned learning tasks from both efficiency and final performance, either or not combined with strong pre-defined augmentations, e. g., on medical images when domain knowledge is unavailable and the existing augmentation techniques perform poorly.
Towards Lightweight Black-Box Attacks against Deep Neural Networks
As it is hard to mitigate the approximation error with few available samples, we propose Error TransFormer (ETF) for lightweight attacks.
Self-Supervision Can Be a Good Few-Shot Learner
Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform self-supervised pre-training.
cross-domain few-shot learning
Unsupervised Few-Shot Image Classification
+1
Bi-Calibration Networks for Weakly-Supervised Video Representation Learning
The video-to-text/video-to-query projections over text prototypes/query vocabulary then start the text-to-query or query-to-text calibration to estimate the amendment to query or text.
Toward Real-world Single Image Deraining: A New Benchmark and Beyond
To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1, 120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
In this work, we propose a novel personalized federated learning framework in a decentralized (peer-to-peer) communication protocol named Dis-PFL, which employs personalized sparse masks to customize sparse local models on the edge.
Prompt Distribution Learning
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks.
Meta Convolutional Neural Networks for Single Domain Generalization
Taking meta features as reference, we propose compositional operations to eliminate irrelevant features of local convolutional features by an addressing process and then to reformulate the convolutional feature maps as a composition of related meta features.
Ranked #5 on
Single-Source Domain Generalization
on Digits-five
Learning To Collaborate in Decentralized Learning of Personalized Models
Decentralized learning (DL) can exploit the images distributed over devices on a network topology to train a global model but is not designed to train personalized models for different tasks or optimize the topology.
Transferrable Contrastive Learning for Visual Domain Adaptation
From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i. e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently.
A Style and Semantic Memory Mechanism for Domain Generalization
Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains.
Ranked #45 on
Domain Generalization
on PACS
Class-Disentanglement and Applications in Adversarial Detection and Defense
In this paper, we propose ''class-disentanglement'' that trains a variational autoencoder $G(\cdot)$ to extract this class-dependent information as $x - G(x)$ via a trade-off between reconstructing $x$ by $G(x)$ and classifying $x$ by $D(x-G(x))$, where the former competes with the latter in decomposing $x$ so the latter retains only necessary information for classification in $x-G(x)$.
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
We then adversarially perturb $G(x)$ in the VAE's bottleneck space and adds it back to the original $R(x)$ as an augmentation, which is therefore sufficiently challenging for contrastive learning and meanwhile preserves the sample identity intact.
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss.
Domain-Class Correlation Decomposition for Generalizable Person Re-Identification
Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training.
Domain Generalization
Generalizable Person Re-identification
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
3D Local Convolutional Neural Networks for Gait Recognition
Second, different body parts possess different scales, and even the same part in different frames can appear at different locations and scales.
Ranked #4 on
Gait Recognition
on OUMVLP
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons.
Learning to Localize Actions from Moments
In this paper, we introduce a new design of transfer learning type to learn action localization for a large set of action categories, but only on action moments from the categories of interest and temporal annotations of untrimmed videos from a small set of action classes.
Transform-Invariant Convolutional Neural Networks for Image Classification and Search
In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage.
Continuous Dropout
On the one hand, continuous dropout is considerably closer to the activation characteristics of neurons in the human brain than traditional binary dropout.
Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks.
Quantization Networks
The proposed quantization function can be learned in a lossless and end-to-end manner and works for any weights and activations of neural networks in a simple and uniform way.
Gaussian Temporal Awareness Networks for Action Localization
Temporally localizing actions in a video is a fundamental challenge in video understanding.
Mocycle-GAN: Unpaired Video-to-Video Translation
Unsupervised image-to-image translation is the task of translating an image from one domain to another in the absence of any paired training examples and tends to be more applicable to practical applications.
Learning Spatio-Temporal Representation with Local and Global Diffusion
Diffusions effectively interact two aspects of information, i. e., localized and holistic, for more powerful way of representation learning.
Ranked #10 on
Action Recognition
on UCF101
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
The whole architecture is then optimized with three consistency regularizations: 1) region-level consistency to align the region-level predictions between teacher and student, 2) inter-graph consistency for matching the graph structures between teacher and student, and 3) intra-graph consistency to enhance the similarity between regions of same class within the graph of student.
Camera Lens Super-Resolution
Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling.
On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning
The objective of our proposed method is to transform the features from different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized.
Towards a Better Match in Siamese Network Based Visual Object Tracker
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance.
Ranked #10 on
Visual Object Tracking
on VOT2017/18
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Under the assumption that the conditional distribution $P(Y|X)$ remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation $T(X)$ by minimizing the discrepancy of the marginal distribution $P(T(X))$.
Ranked #76 on
Domain Generalization
on PACS
Deep Boosting for Image Denoising
Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks.
Domain Generalization via Conditional Invariant Representation
With the conditional invariant representation, the invariance of the joint distribution $\mathbb{P}(h(X), Y)$ can be guaranteed if the class prior $\mathbb{P}(Y)$ does not change across training and test domains.
Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition
Considering the complementarity between graph node convolution and graph edge convolution, we additionally construct two hybrid neural networks to combine graph node convolutional neural network and graph edge convolutional neural network using shared intermediate layers.
A Twofold Siamese Network for Real-Time Object Tracking
SA-Siam is composed of a semantic branch and an appearance branch.
Ranked #1 on
Visual Object Tracking
on OTB-50
