Search Results for author:
Found 46 papers, 28 papers with code
Dare to Plagiarize? Plagiarized Painting Recognition and Retrieval
The finetuned model greatly improves retrieval performance by 12\% AP over the baseline, though it unexpectedly results in a lower recognition accuracy (92. 7\%).
Attention to Burstiness: Low-Rank Bilinear Prompt Tuning
Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts.
Robust Few-Shot Vision-Language Model Adaptation
SRAPF consists of two stages: (1) partial finetuning the visual encoder using both ID and retrieved data, and (2) adversarial partial finetuning with few-shot ID data.
Solving Instance Detection from an Open-World Perspective
Instance detection (InsDet) aims to localize specific object instances within a novel scene imagery based on given visual references.
UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
To explore foundation models' capability in localizing unusual activity, we introduce UAL-Bench, a comprehensive benchmark for unusual activity localization, featuring three video datasets: UAG-OOPS, UAG-SSBD, UAG-FunQA, and an instruction-tune dataset: OOPS-UAG-Instruct, to improve model capabilities.
Lidar Panoptic Segmentation in an Open World
To address this unrealistic assumption, we study LPS in the Open World (LiPSOW): we train models on a dataset with a pre-defined semantic class vocabulary and study their generalization to a larger dataset where novel instances of thing and stuff classes can appear.
LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies
We assess 75 models using ImageNet as the ID dataset and five significantly shifted OOD variants, uncovering a strong linear correlation between ID LCA distance and OOD top-1 accuracy.
Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
Second, more surprisingly, we find that simply finetuning a VLM solely on few-shot examples significantly outperforms previous FSR methods, and finetuning on the mix of retrieved and few-shot data yields even better results.
CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching
Moreover, all existing methods match crime-scene shoeprints to clean reference prints, yet our analysis shows matching to more informative tread depth maps yields better retrieval results.
Roadside Monocular 3D Detection via 2D Detection Prompting
Our method builds on a key insight that, compared with 3D detectors, a 2D detector is much easier to train and performs significantly better w. r. t detections on the 2D image plane.
Boosting Image Restoration via Priors from Pre-trained Models
Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions.
AccessLens: Auto-detecting Inaccessibility of Everyday Objects
In our increasingly diverse society, everyday physical interfaces often present barriers, impacting individuals across various contexts.
The Neglected Tails in Vision-Language Models
We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts.
Revisiting Few-Shot Object Detection with Vision-Language Models
Concretely, we propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external data and fine-tuned on multi-modal (text and visual) K-shot examples per target class.
Long-Tailed 3D Detection via Multi-Modal Fusion
Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale multi-modal (LiDAR + RGB) data.
Instance Tracking in 3D Scenes from Egocentric Videos
We explore this problem by first introducing a new benchmark dataset, consisting of RGB and depth videos, per-frame camera pose, and instance-level annotations in both 2D camera and 3D world coordinates.
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents.
Prompting Scientific Names for Zero-Shot Species Recognition
We find that common names are more likely to be included in CLIP's training set, and prompting them achieves 2$\sim$5 times higher accuracy on benchmarking datasets of fine-grained species recognition.
OV-PARTS: Towards Open-Vocabulary Part Segmentation
Secondly, part segmentation introduces an open granularity challenge due to the diverse and often ambiguous definitions of parts in the open world.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
Improving Knowledge Distillation via Regularizing Feature Norm and Direction
Finally, we propose a rather simple loss term (dubbed ND loss) to simultaneously (1) encourage student to produce large-\emph{norm} features, and (2) align the \emph{direction} of student features and teacher class-means.
Ranked #1 on
Knowledge Distillation
on COCO 2017 val
Far3Det: Towards Far-Field 3D Detection
We focus on the task of far-field 3D detection (Far3Det) of objects beyond a certain distance from an observer, e. g., $>$50m.
Towards Long-Tailed 3D Detection
Moreover, semantic classes are often organized within a hierarchy, e. g., tail classes such as child and construction-worker are arguably subclasses of pedestrian.
Continual Learning with Evolving Class Ontologies
LECO requires learning classifiers in distinct time periods (TPs); each TP introduces a new ontology of "fine" labels that refines old ontologies of "coarse" labels (e. g., dog breeds that refine the previous ${\tt dog}$).
Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos
We develop a method termed ShoeRinsics that learns to predict depth by leveraging a mix of fully supervised synthetic data and unsupervised retail image data.
Long-Tailed Recognition via Weight Balancing
In contrast, weight decay penalizes larger weights more heavily and so learns small balanced weights; the MaxNorm constraint encourages growing small weights within a norm ball but caps all the weights by the radius.
Ranked #9 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Multimodal Object Detection via Probabilistic Ensembling
Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs).
Ranked #2 on
Object Detection
on InOutDoor
OpenGAN: Open-Set Recognition via Open Data Generation
However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which are unlikely to exhaustively span the open-world.
An Empirical Exploration of Open-Set Recognition via Lightweight Statistical Pipelines
Machine-learned safety-critical systems need to be self-aware and reliably know their unknowns in the open-world.
Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias
We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses.
Weak Supervision and Referring Attention for Temporal-Textual Association Learning
The referring attention is our designed mechanism acting as a scoring function for grounding the given queries over frames temporally.
Celeganser: Automated Analysis of Nematode Morphology and Age
The nematode Caenorhabditis elegans (C. elegans) serves as an important model organism in a wide variety of biological studies.
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
In this setting, we find that existing domain translation approaches are difficult to train and offer little advantage over simple baselines that use a mix of real and synthetic data.
Modularized Textual Grounding for Counterfactual Resilience
Computer Vision applications often require a textual grounding module with precision, interpretability, and resilience to counterfactual inputs/queries.
Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos.
Image Reconstruction with Predictive Filter Flow
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution.
Ranked #32 on
Image Super-Resolution
on Set14 - 4x upscaling
Pixel-wise Attentional Gating for Parsimonious Pixel Labeling
To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each layer of a deep convolutional network.
Ranked #7 on
Semantic Segmentation
on KITTI Semantic Segmentation
Fine-Grained Facial Expression Analysis Using Dimensional Emotion Model
Specifically, we first mapped facial expressions into dimensional measures so that we transformed facial expression analysis from a classification problem to a regression one.
Weakly Supervised Attention Learning for Textual Phrases Grounding
Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction.
Recurrent Pixel Embedding for Instance Grouping
We introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components.
Recurrent Scene Parsing with Perspective Understanding in the Loop
We propose a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale (inversely proportional to the depth) so that small details are preserved for distant objects while larger receptive fields are used for those nearby.
Ranked #40 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Low-rank Bilinear Pooling for Fine-Grained Classification
To address the computational demands of high feature dimensionality, we propose to represent the covariance features as a matrix and apply a low-rank bilinear classifier.
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function.
Ranked #7 on
Aesthetics Quality Assessment
on AVA
Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification
We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology.
Collaborative Receptive Field Learning
However, measuring pairwise distance of RF's for building the similarity graph is a nontrivial problem.
Learning Mid-Level Features and Modeling Neuron Selectivity for Image Classification
We now know that mid-level features can greatly enhance the performance of image learning, but how to automatically learn the image features efficiently and in an unsupervised manner is still an open question.
