Search Results for author:
Found 20 papers, 9 papers with code
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
In this work, we re-formulate the model compression problem into the customized compensation problem: Given a compressed model, we aim to introduce residual low-rank paths to compensate for compression errors under customized requirements from users (e. g., tasks, compression ratios), resulting in greater flexibility in adjusting overall capacity without being constrained by specific compression formats.
SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
Large-scale vision-language models, such as CLIP, are known to contain harmful societal bias regarding protected attributes (e. g., gender and age).
GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation
With the proposed TAP-CL, our GroPrompt framework can generate temporal-consistent yet text-aware position prompts describing locations and movements for the referred object from the video.
MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model.
DoRA: Weight-Decomposed Low-Rank Adaptation
By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead.
Ranked #2 on
parameter-efficient fine-tuning
on WinoGrande
(using extra training data)
Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation
To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories.
Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter
However, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm.
Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation
To leverage robust representations from large-scale models while enabling efficient model personalization for heterogeneous clients, we propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG), which learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions.
QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023.
A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofing
Face anti-spoofing (FAS) is indispensable for a face recognition system.
Kinship Representation Learning with Face Componential Relation
Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem.
Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss
With the increasing variations of face presentation attacks, model generalization becomes an essential challenge for a practical face anti-spoofing system.
MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition
In this paper, we propose MixFairFace framework to improve the fairness in face recognition models.
Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation
Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model.
PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition
Previous works leverage auxiliary pixel-level supervision and domain generalization approaches to address unseen spoof types.
FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition
Current state-of-the-art deep learning based face recognition (FR) models require a large number of face identities for central training.
High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network
Our DepthNet is used to augment a large 2D face image dataset to a large RGB-D face dataset, which is used for training an accurate RGB-D face recognition model.
Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing
Unlike previous FAS disentanglement works with one-stage architecture, we found that the dual-stage training design can improve the training stability and effectively encode the features to detect unseen attack types.
Unified Representation Learning for Cross Model Compatibility
We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications.
Robust Image Segmentation Using Contour-Guided Color Palettes
The contour-guided color palette (CCP) is proposed for robust image segmentation.
