Search Results for author:
Found 104 papers, 69 papers with code
API-Net: Robust Generative Classifier via a Single Discriminator
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
Vision Calorimeter for Anti-neutron Reconstruction: A Baseline
In this study, we introduce Vision Calorimeter (ViC), a baseline method for anti-neutron reconstruction that leverages deep learning detectors to analyze the implicit relationships between EMC responses and incident $\bar{n}$ characteristics.
Depth-guided Texture Diffusion for Image Semantic Segmentation
By integrating this enriched depth map with the original RGB image into a joint feature embedding, our method effectively bridges the disparity between the depth map and the image, enabling more accurate semantic segmentation.
Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
In SfM-free methods, inaccurate initial poses lead to misalignment issue, which, under the constraints of per-pixel image loss functions, results in excessive gradients, causing unstable optimization and poor convergence for NVS.
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
For this purpose, we establish a new benchmark comprising text prompts that fully reflect multiple dynamics grades, and define a set of dynamics scores corresponding to various temporal granularities to comprehensively evaluate the dynamics of each generated video.
ClawMachine: Fetching Visual Tokens as An Entity for Referring and Grounding
Existing methods, including proxy encoding and geometry encoding, incorporate additional syntax to encode the object's location, bringing extra burdens in training MLLMs to communicate between language and vision.
Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian
3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis.
vHeat: Building Vision Models upon Heat Conduction
A fundamental problem in learning robust and expressive visual representations lies in efficiently estimating the spatial relationships of visual semantics throughout the entire image.
DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Unfortunately, most of existing methods using fixed visual inputs remain lacking the resolution adaptability to find out precise language descriptions.
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation
To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings.
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts.
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection
Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections.
Ranked #2 on
3D Object Detection
on nuScenes Camera Only
Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
Multidomain crowd counting aims to learn a general model for multiple diverse datasets.
ControlCap: Controllable Region-level Captioning
The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue.
Ranked #1 on
Dense Captioning
on Visual Genome
CPR++: Object Localization via Single Coarse Point Supervision
CPR reduces the semantic variance by selecting a semantic centre point in a neighbourhood region to replace the initial annotated point.
ChatterBox: Multi-round Multimodal Referring and Grounding
In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues.
VMamba: Visual State Space Model
Designing computationally efficient network architectures persists as an ongoing necessity in computer vision.
Regressor-Segmenter Mutual Prompt Learning for Crowd Counting
In this study, we propose mutual prompt learning (mPrompt), which leverages a regressor and a segmenter as guidance for each other, solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background.
Spatial Transform Decoupling for Oriented Object Detection
Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks.
Ranked #2 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Generative Prompt Model for Weakly Supervised Object Localization
During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric, using extra
training data)
Album Storytelling with Iterative Story-aware Captioning and Large Language Models
One natural approach is to use caption models to describe each photo in the album, and then use LLMs to summarize and rewrite the generated captions into an engaging story.
Generic-to-Specific Distillation of Masked Autoencoders
Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms.
Spectral Aware Softmax for Visible-Infrared Person Re-Identification
Based on the observation and analysis of SA-Softmax, we modify the SA-Softmax with the Feature Mask and Absolute-Similarity Term to alleviate the ambiguous optimization during model training.
Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning
The knowledge transfer between two networks is based on an asymmetric mutual learning manner.
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
Proposal Distribution Calibration for Few-Shot Object Detection
Adapting object detectors learned with sufficient supervision to novel classes under low data regimes is charming yet challenging.
CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection
In this paper we propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects: focusing on it again, at a finer scale, if the object can not be identified clearly for the first time.
Feature Calibration Network for Occluded Pedestrian Detection
FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module.
Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration
iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT).
Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning
In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.
A Unified View of Masked Image Modeling
Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks.
Multi-Agent Automated Machine Learning
In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML).
Learnable Distribution Calibration for Few-Shot Class-Incremental Learning
LDC is built upon a parameterized calibration unit (PCU), which initializes biased distributions for all classes based on classifier vectors (memory-free) and a single covariance matrix.
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
The large-size BEiT v2 obtains 87. 3% top-1 accuracy for ImageNet-1K (224 size) fine-tuning, and 56. 7% mIoU on ADE20K for semantic segmentation.
Ranked #27 on
Self-Supervised Image Classification
on ImageNet
Point-to-Box Network for Accurate Object Detection via Single Point Supervision
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models.
Ranked #5 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers
The past year has witnessed a rapid development of masked image modeling (MIM).
Object Localization under Single Coarse Point Supervision
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
Global2Local: A Joint-Hierarchical Attention for Video Captioning
Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as their spatial-temporal correlations from the redundant frames and semantic content.
CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
Semi-supervised object detection has recently achieved substantial progress.
P2P-Loc: Point to Point Tiny Person Localization
As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way.
Exploring Complicated Search Spaces with Interleaving-Free Sampling
In this paper, we build the search algorithm upon a complicated search space with long-distance connections, and show that existing weight-sharing search algorithms mostly fail due to the existence of \textbf{interleaved connections}.
Self-supervised Feature-Gate Coupling for Dynamic Network Pruning
Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features.
Semantic-Aware Generation for Self-Supervised Visual Representation Learning
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.
Ranked #63 on
Semantic Segmentation
on Cityscapes test
Long-tailed Distribution Adaptation
We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.
GraFormer: Graph Convolution Transformer for 3D Pose Estimation
Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation.
Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps.
Rethinking Sampling Strategies for Unsupervised Person Re-identification
While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role.
Cogradient Descent for Dependable Learning
Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative.
Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects.
Ranked #34 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation
Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with few-shot examples.
Ranked #71 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
Conformer: Local Features Coupling Global Representations for Visual Recognition
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.
Ranked #329 on
Image Classification
on ImageNet
Multiple instance active learning for object detection
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection.
Ranked #1 on
Active Object Detection
on MS COCO
Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning
By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization.
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
Ranked #16 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Harmonic Feature Activation for Few-Shot Semantic Segmentation
HFA is formulated as a bilinear model, which takes charge of the pixel-wise dense correlation (bilinear feature activation) between query and support images in a systematic way.
Network Pruning using Adaptive Exemplar Filters
Inspired by the face recognition community, we use a message passing algorithm Affinity Propagation on the weight matrices to obtain an adaptive number of exemplars, which then act as the preserved filters.
Self-Motivated Communication Agent for Real-World Vision-Dialog Navigation
Vision-Dialog Navigation (VDN) requires an agent to ask questions and navigate following the human responses to find target objects.
Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID
To avoid such problematic models in occluded person ReID, we propose the Occlusion-Aware Mask Network (OAMN).
Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications.
Adaptive Linear Span Network for Object Skeleton Detection
Conventional networks for object skeleton detection are usually hand-crafted.
The 1st Tiny Object Detection Challenge:Methods and Results
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
Prototype Mixture Models for Few-shot Semantic Segmentation
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose.
Component Divide-and-Conquer for Real-World Image Super-Resolution
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
This drawback limits the flexibility of UDA in complicated open-set tasks where no labels are shared between domains.
Discretization-Aware Architecture Search
The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods.
Progressive Cluster Purification for Unsupervised Feature Learning
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored.
Domain Adaptive Person Re-Identification
Ensemble Learning
+1
Domain Contrast for Domain Adaptive Object Detection
We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors.
iffDetector: Inference-aware Feature Filtering for Object Detection
In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages.
Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.
Cogradient Descent for Bilinear Optimization
Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure.
Rethinking Performance Estimation in Neural Architecture Search
In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space.
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown.
Ranked #9 on
Unsupervised Domain Adaptation
on Duke to Market
Architecture Disentanglement for Deep Neural Networks
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
In this work, we propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains while considering the instantaneous alignment difficulty.
Filter Sketch for Network Pruning
Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure.
Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on
Self-supervised Video Retrieval
on HMDB51
Scale Match for Tiny Person Detection
In this paper, we introduce a new benchmark, referred to as TinyPerson, opening up a promising directionfor tiny object detection in a long distance and with mas-sive backgrounds.
Multiple Anchor Learning for Visual Object Detection
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #117 on
Object Detection
on COCO test-dev
SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
Modern visual trackers usually construct online learning models under the assumption that the feature response has a Gaussian distribution with target-centered peak response.
FreeAnchor: Learning to Match Anchors for Visual Object Detection
In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner.
Ranked #136 on
Object Detection
on COCO test-dev
Information Competing Process for Learning Diversified Representations
Learning representations with diversified information remains as an open problem.
Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
Especially, AGUIT benefits from two-fold: (1) It adopts a novel semi-supervised learning process by translating attributes of labeled data to unlabeled data, and then reconstructing the unlabeled data by a cycle consistency operation.
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
Ranked #15 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.
Min-Entropy Latent Model for Weakly Supervised Object Detection
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images
In particular, the advantage of CHR is more significant in the scenarios with fewer positive training samples, which demonstrates its potential application in real-world security inspection.
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.
Linear Span Network for Object Skeleton Detection
Hinted by this, we formalize a Linear Span framework, and propose Linear Span Network (LSN) modified by Linear Span Units (LSUs), which minimize the reconstruction error of convolutional network.
SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond
The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages.
Weakly Supervised Instance Segmentation using Class Peak Response
Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.
Ranked #13 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
General Classification
Image-level Supervised Instance Segmentation
+3
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.
Soft Proposal Networks for Weakly Supervised Object Localization
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.
Ranked #2 on
Weakly Supervised Object Detection
on MS COCO
Deep Spatio-temporal Manifold Network for Action Recognition
Visual data such as videos are often sampled from complex manifold.
SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
By stacking RUs in a deep-to-shallow manner, SRN exploits the 'flow' of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales.
A Graphical Social Topology Model for Multi-Object Tracking
Inspired with the social affinity property of moving objects, we propose a Graphical Social Topology (GST) model, which estimates the group dynamics by jointly modeling the group structure and the states of objects using a topological representation.
Oriented Response Networks
DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks.
Ranked #83 on
Image Classification
on CIFAR-100
(using extra training data)
Output Constraint Transfer for Kernelized Correlation Filter in Tracking
Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers.
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.
A scalable convolutional neural network for task-specified scenarios via knowledge distillation
In this paper, we explore the redundancy in convolutional neural network, which scales with the complexity of vision tasks.
