Search Results for author:
Found 59 papers, 47 papers with code
Model Stock: All we need is just a few fine-tuned models
This paper introduces an efficient fine-tuning method for large pre-trained models, offering strong in-distribution (ID) and out-of-distribution (OOD) performance.
Toward Interactive Regional Understanding in Vision-Large Language Models
Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements.
Rotary Position Embedding for Vision Transformer
This study provides a comprehensive analysis of RoPE when applied to ViTs, utilizing practical implementations of RoPE for 2D vision data.
Calibrating Large Language Models Using Their Generations Only
As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important.
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them.
Compressed Context Memory For Online Language Model Interaction
This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands.
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
Match me if you can: Semantic Correspondence Learning with Unpaired Images
Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points.
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4.
Masking Augmentation for Supervised Learning
In this paper, we propose a novel way to involve masking augmentations dubbed Masked Sub-model (MaskSub).
MPCHAT: Towards Multimodal Persona-Grounded Conversation
In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities.
Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Recent advances in Large Language Models (LLMs) have stimulated a surge of research aimed at extending their applications to the visual domain.
Who Wrote this Code? Watermarking for Code Generation
Based on \citet{Kirchenbauer2023watermark}, we propose a new watermarking method, Selective WatErmarking via Entropy Thresholding (SWEET), that promotes "green" tokens only at the position with high entropy of the token distribution during generation, thereby preserving the correctness of the generated code.
What Do Self-Supervised Vision Transformers Learn?
We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks.
RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
In this paper, we propose a robustness benchmark for image-text matching models to assess their vulnerabilities.
Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs).
Ranked #6 on
3D Multi-Person Pose Estimation
on MuPoTS-3D
Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
We refer to the new paradigm of training models with annotation byproducts as learning using annotation byproducts (LUAB).
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion.
Ranked #3 on
Zero-Shot Composed Image Retrieval (ZS-CIR)
on CIRCO
SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e. g., the LAION-4B dataset needs 240TB storage space).
Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
To this end, we present scalable and effective algorithms for detecting label errors and outlier data based on the relational graph structure of data.
Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts
We refer to the new paradigm of training models with annotation byproducts as learning using annotation byproducts (LUAB).
Group Generalized Mean Pooling for Vision Transformer
As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.
A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective
Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level regularization of the underlying training loss and a regularization of the first layer parameters.
Exploring Temporally Dynamic Data Augmentation for Video Recognition
The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations.
Dataset Condensation via Efficient Synthetic-Data Parameterization
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (e. g. train and rail), fundamentally bounding the performance of WSSS.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Dataset Condensation with Contrastive Signals
However, in this study, we prove that the existing DC methods can perform worse than the random selection method when task-irrelevant information forms a significant part of the training dataset.
Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning
In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling.
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes.
Ranked #20 on
Long-tail Learning
on ImageNet-LT
OCR-free Document Understanding Transformer
Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
Ranked #10 on
Document Image Classification
on RVL-CDIP
Observations on K-image Expansion of Image-Mixing Augmentation for Classification
Image-mixing augmentations (e. g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification.
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
This phenomenon, also known as shortcut learning, is emerging as a key limitation of the current generation of machine learning models.
Progressive Transmission and Inference of Deep Learning Models
On the server-side, a deep learning model is divided and progressively transmitted to the user devices.
Normalization Matters in Weakly Supervised Object Localization
Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information.
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model.
Rethinking Spatial Dimensions of Vision Transformers
We empirically show that such a spatial dimension reduction is beneficial to a transformer architecture as well, and propose a novel Pooling-based Vision Transformer (PiT) upon the original ViT model.
Ranked #333 on
Image Classification
on ImageNet
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
However, they have not fixed the training set, presumably because of a formidable annotation cost.
Ranked #20 on
Image Classification
on OmniBenchmark
VideoMix: Rethinking Data Augmentation for Video Classification
Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers.
Rethinking Channel Dimensions for Efficient Model Design
We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction.
Ranked #290 on
Image Classification
on ImageNet
(using extra training data)
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
Because of the scale invariance, this modification only alters the effective step sizes without changing the effective update directions, thus enjoying the original convergence properties of GD optimizers.
An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans.
Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
We first assume that the priors of future samples can be generated in an independently and identically distributed (i. i. d.)
Learning De-biased Representations with Biased Representations
This tactic is feasible in many scenarios where it is much easier to define a set of biased representations than to define and quantify bias.
Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.
EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD), less than 0. 1 million, as well as achieving comparable performance to deep heavy detectors.
Ranked #23 on
Face Detection
on WIDER Face (Hard)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
A Comprehensive Overhaul of Feature Distillation
We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function.
Ranked #38 on
Knowledge Distillation
on ImageNet
Character Region Awareness for Text Detection
Scene text detection methods based on neural networks have emerged recently and have shown promising results.
Ranked #1 on
Scene Text Detection
on ICDAR 2013
(Precision metric)
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Many new proposals for scene text recognition (STR) models have been introduced in recent years.
Ranked #7 on
Scene Text Recognition
on ICDAR 2003
C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation
To resolve this problem, we propose a new block called Concentrated-Comprehensive Convolution (C3) which applies the asymmetric convolutions before the depth-wise separable dilated convolution to compensate for the information loss due to dilated convolution.
Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neurons.
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier.
Context-aware Deep Feature Compression for High-speed Visual Tracking
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.
Ranked #15 on
Visual Object Tracking
on VOT2017/18
Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
In addition to this performance enhancement problem, we show that the proposed PGN can be adopted to solve the classical adversarial problem without utilizing the information on the target classifier.
Attentional Correlation Filter Network for Adaptive Visual Tracking
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.
Palettenet: Image recolorization with given color palette
PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette.
Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning
In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale.
Unsupervised Holistic Image Generation from Key Local Patches
We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior.
Visual Path Prediction in Complex Scenes With Crowded Moving Objects
In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects.
