Search Results for author:
Found 102 papers, 46 papers with code
The 7th AI City Challenge
The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.
Large-scale Training Data Search for Object Re-identification
We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained.
A Bag-of-Prototypes Representation for Dataset-Level Applications
The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model.
Learning to Select Camera Views: Efficient Multiview Understanding at Few Glances
Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage.
Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift
In other words, a calibrator optimal on the calibration set would be suboptimal on the OOD test set and thus has degraded performance.
Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective
We further provide interesting analyses of the effects of backbones and IND/OOD datasets on OOD detection performance.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
This work aims to assess how well a model performs under distribution shifts without using labels.
Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding
Specifically, the proposed model introduces semantic descriptions consisting of network-wide spatial and temporal information of traffic data to help the GT-TDI model capture spatiotemporal correlations at a network level.
CircNet: Meshing 3D Point Clouds with Circumcenter Detection
In this paper, we leverage the duality between a triangle and its circumcenter, and introduce a deep neural network that detects the circumcenters to achieve point cloud triangulation.
High-Fidelity Guided Image Synthesis with Latent Diffusion Models
The user scribbles control the color composition while the text prompt provides control over the overall image semantics.
Generalizable Re-Identification from Videos with Cycle Association
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos.
Domain Generalization
Generalizable Person Re-identification
+1
Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation
In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-correlation matrices and matches them across views to provide robust supervision.
Learning to Structure an Image with Few Colors and Beyond
To this end, we propose a color quantization network, ColorCNN, which learns to structure an image in limited color spaces by minimizing the classification loss.
Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing
In particular, we propose a novel approach paint2pix, which learns to predict (and adapt) "what a user wants to draw" from rudimentary brushstroke inputs, by learning a mapping from the manifold of incomplete human paintings to their realistic renderings.
On the Strong Correlation Between Model Invariance and Generalization
Generalization and invariance are two essential properties of any machine learning model.
Multiview Detection with Cardboard Human Modeling
In this paper, we propose a new pedestrian representation scheme based on human point clouds modeling.
The 6th AI City Challenge
The four challenge tracks of the 2022 AI City Challenge received participation requests from 254 teams across 27 countries.
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond
This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.
Intelli-Paint: Towards Developing Human-like Painting Agents
However, current research in this direction is often reliant on a progressive grid-based division strategy wherein the agent divides the overall image into successively finer grids, and then proceeds to paint each of them in parallel.
Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking
In this paper, we design experiments to verify such misfit between global re-ID feature distances and local matching in tracking, and propose a simple yet effective approach to adapt affinity estimations to corresponding matching scopes in MTMCT.
How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?
To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data.
Label-Free Model Evaluation with Semi-Structured Dataset Representations
In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression.
Hierarchical Image Classification with A Literally Toy Dataset
We define the classification task where classes have characteristics above and the flat classes and the base classes are organized hierarchically as hierarchical image classification.
Memory-Free Generative Replay For Class-Incremental Learning
With the absence of old task images, they often assume that old knowledge is well preserved if the classifier produces similar output on new images.
Ranking Models in Unlabeled New Environments
For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates.
Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)
Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation.
Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking
We show that compared with real data, association knowledge obtained from synthetic data can achieve very similar performance on real-world test sets without domain adaption techniques.
Invertible Attention
Attention has been proved to be an efficient mechanism to capture long-range dependencies.
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
In this work, we train semantic classification and rotation prediction in a multi-task way.
VTNet: Visual Transformer Network for Object Goal Navigation
In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation.
Boosting Semi-Supervised Face Recognition with Noise Robustness
This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling.
Visualizing Adapted Knowledge in Domain Transfer
We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains.
Positive Sample Propagation along the Audio-Visual Event Line
To encourage the network to extract high correlated features for positive samples, a new audio-visual pair similarity loss is proposed.
Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning
However, we argue that the sample variance for a multi-scene environment is best minimized by treating each scene as a distinct MDP, and then learning a joint value function V(s, M) dependent on both state s and MDP M. We further demonstrate that the true joint value function for a multi-scene environment, follows a multi-modal distribution which is not captured by traditional CNN / LSTM based critic networks.
Fine-grained Classification via Categorical Memory Networks
The memory module stores the prototypical feature representation for each category as a moving average.
Ranked #48 on
Fine-Grained Image Classification
on CUB-200-2011
Enhanced Scene Specificity with Sparse Dynamic Value Estimation
Recently, Singh et al. [1] tried to address this by proposing a dynamic value estimation approach that models the true joint value function distribution as a Gaussian mixture model (GMM).
Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings
2) We also introduce invariance to the position and scale of the foreground object through a neural alignment model, which combines object localization and spatial transformer networks in an end to end manner, to zoom into a particular semantic instance.
Model-based Reinforcement Learning
reinforcement-learning
+1
Source Free Domain Adaptation with Image Translation
In this paper, we study the problem of source free domain adaptation (SFDA), whose distinctive feature is that the source domain only provides a pre-trained model, but no source data.
Learning Object Relation Graph and Tentative Policy for Visual Navigation
Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN).
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
Multiview Detection with Feature Perspective Transformation
First, how should we aggregate cues from the multiple views?
Are Labels Always Necessary for Classifier Accuracy Evaluation?
As the classification accuracy of the model on each sample (dataset) is known from the original dataset labels, our task can be solved via regression.
Learning to simulate complex scenes
To optimize the attribute values and obtain a training set of similar content to real-world data, we propose a scalable discretization-and-relaxation (SDR) approach.
Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning
Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world.
Correlating Edge, Pose with Parsing
Compared with the existing practice of feature concatenation, we find that uncovering the correlation among the three factors is a superior way of leveraging the pivotal contextual cues provided by edges and poses.
Learning to Structure an Image with Few Colors
Color and structure are the two pillars that construct an image.
Circle Loss: A Unified Perspective of Pair Similarity Optimization
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Simulating Content Consistent Vehicle Datasets with Attribute Descent
Between synthetic and real data, there is a two-level domain gap, i. e., content level and appearance level.
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
Due to the continuity of target trajectories, tracking systems usually restrict their data association within a local neighborhood.
Towards Real-Time Multi-Object Tracking
In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
Ranked #4 on
Multi-Object Tracking
on HiEve
Learning to Adapt Invariance in Memory for Person Re-identification
This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain.
Ranked #7 on
Unsupervised Domain Adaptation
on Market to MSMT
Joint Discriminative and Generative Learning for Person Re-identification
To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.
Ranked #1 on
Person Re-Identification
on UAV-Human
Image-to-Image Translation
Unsupervised Domain Adaptation
+1
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Linkage Based Face Clustering via Graph Convolution Network
The key idea is that we find the local context in the feature space around an instance (face) contains rich information about the linkage relationship between this instance and its neighbors.
Image Classification base on PCA of Multi-view Deep Representation
In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data.
Learning from Web Data: the Benefit of Unsupervised Object Localization
In this work, we first systematically study the built-in gap between the web and standard datasets, i. e. different data distributions between the two kinds of data.
Dissecting Person Re-identification from the Viewpoint of Viewpoint
Second, on the 3D data engine, we quantitatively analyze the influence of pedestrian rotation angle on re-ID accuracy.
Domain Alignment with Triplets
When aligning the distributions in the embedding space, SCA enforces a similarity-preserving constraint to maintain class-level relations among the source and target images, i. e., if a source image and a target image are of the same class label, their corresponding embeddings are supposed to be aligned nearby, and vise versa.
Similarity-preserving Image-image Domain Adaptation for Person Re-identification
It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image.
Query Adaptive Late Fusion for Image Retrieval
That is to say, for some queries, a feature may be neither discriminative nor complementary to existing ones, while for other queries, the feature suffices.
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
We consider the problem of unsupervised domain adaptation in semantic segmentation.
Ranked #8 on
Semantic Segmentation
on DADA-seg
Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
Generalizing A Person Retrieval Model Hetero- and Homogeneously
Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.
Attention-based Pyramid Aggregation Network for Visual Place Recognition
Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task.
Macro-Micro Adversarial Network for Human Parsing
To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN).
Ranked #10 on
Semantic Segmentation
on LIP val
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
This paper considers the task of thorax disease classification on chest X-ray images.
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
Second, we estimate the posterior label distribution of the unlabeled data for target network training.
Camera Style Adaptation for Person Re-identification
In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation.
Ranked #69 on
Person Re-Identification
on DukeMTMC-reID
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
Dual-Path Convolutional Image-Text Embeddings with Instance Loss
In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space.
Ranked #1 on
Cross-Modal Retrieval
on CUHK-PEDES
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
Label estimation is an important component in an unsupervised person re-identification (re-ID) system.
Ranked #8 on
Person Re-Identification
on PRID2011
Random Erasing Data Augmentation
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #4 on
Image Classification
on Fashion-MNIST
PatchShuffle Regularization
This paper focuses on regularizing the training of the convolutional neural network (CNN).
Pedestrian Alignment Network for Large-scale Person Re-identification
This task aims to search a query person in a large image pool.
Ranked #1 on
Person Re-Identification
on CUHK03 (detected)
Few-Example Object Detection with Model Communication
Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.
Ranked #1 on
Weakly Supervised Object Detection
on COCO
Unsupervised Person Re-identification: Clustering and Fine-tuning
Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence.
Ranked #10 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
Part-based Deep Hashing for Large-scale Person Re-identification
In the experiment, we show that the proposed Part-based Deep Hashing method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.
Improving Person Re-identification by Attribute and Identity Learning
Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions.
Ranked #73 on
Person Re-Identification
on DukeMTMC-reID
Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval
Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications.
SVDNet for Pedestrian Retrieval
This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID).
Ranked #14 on
Person Re-Identification
on CUHK03 detected
A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
Additionally, a trivial solution, \ie, directly using the predicted class label for cross-media retrieval, is tested.
Re-ranking Person Re-identification with k-reciprocal Encoding
Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance.
Ranked #11 on
Person Re-Identification
on CUHK03
Pose Invariant Embedding for Deep Person Re-identification
Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input.
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
We verify the proposed method on a practical problem: person re-identification (re-ID).
Ranked #4 on
Person Re-Identification
on CUHK03
Fine-Grained Image Classification
Person Re-Identification
+1
A Discriminatively Learned CNN Embedding for Person Re-identification
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i. e, verification and classification models.
Ranked #1 on
Person Re-Identification
on Market-1501+500k
Person Re-identification: Past, Present and Future
Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance.
Ranked #81 on
Person Re-Identification
on DukeMTMC-reID
SIFT Meets CNN: A Decade Survey of Instance Retrieval
This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.
Coarse2Fine: Two-Layer Fusion For Image Retrieval
Departing from the previous methods fusing multiple image descriptors simultaneously, C2F is featured by a layered procedure composed by filtering and refining.
InterActive: Inter-Layer Activeness Propagation
An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network.
Person Re-identification in the Wild
Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification.
Good Practice in CNN Feature Transfer
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification.
Scalable Person Re-Identification: A Benchmark
As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor.
Ranked #88 on
Person Re-Identification
on DukeMTMC-reID
Query-Adaptive Late Fusion for Image Search and Person Re-Identification
However, in a more realistic situation, one does not know in advance whether a feature is effective or not for a given query.
Person Re-identification Meets Image Search
In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem.
Visual Reranking with Improved Image Graph
This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search.
Seeing the Big Picture: Deep Embedding with Contextual Evidences
Specifically, the Convolutional Neural Network (CNN) is employed to extract features from regional and global patches, leading to the so-called "Deep Embedding" framework.
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval
Albeit simple, Bayes merging can be well applied in various merging tasks, and consistently improves the baselines on multi-vocabulary merging.
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval
Specifically, we exploit the fusion of local color feature into c-MI.
Lp-Norm IDF for Large Scale Image Search
Further, by counting for the term-frequency in each image, the proposed L p -norm IDF helps to alleviate the visual word burstiness phenomenon.
