Search Results for author:
Found 338 papers, 144 papers with code
Wavelet-Based Dual-Branch Network for Image Demoiréing
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
Large-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery
It is a challenging problem since (1) the identifying process is susceptible to over-fitting with limited samples of an object, and (2) the sample imbalance between a base (known knowledge) category and a novel category is easy to bias the recognition results.
Extract and Merge: Superpixel Segmentation with Regional Attributes
For a certain object in an image, the relationship between its central region and the peripheral region is not well utilized in existing superpixel segmentation methods.
FTL: A universal framework for training low-bit DNNs via Feature Transfer
Compared with low-bit models trained directly, the proposed framework brings 0. 5% to 3. 4% accuracy gains to three different quantization schemes.
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.
Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision
In this paper, we rethink implicit reasoning process in VQA, and propose a new formulation which maximizes the log-likelihood of joint distribution for the observed question and predicted answer.
HunyuanVideo: A Systematic Framework For Large Video Generative Models
In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains.
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
Coupling with these two designs enables us to generate higher-resolution outpainting videos with rich content while keeping spatial and temporal consistency.
SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges.
Segment Any 4D Gaussians
However, there is a dearth of research focusing on segmentation within 4D representations.
Aligning Human Motion Generation with Human Perceptions
Human motion generation is a critical task with a wide range of applications.
GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
The main idea is to bind Gaussians to reasonable geometry, which evolves over the whole generation process.
Text-Animator: Controllable Visual Text Video Generation
Video generation is a challenging yet pivotal task in various industries, such as gaming, e-commerce, and advertising.
OVMR: Open-Vocabulary Recognition with Multi-Modal References
Existing works have proposed different methods to embed category cues into the model, \eg, through few-shot fine-tuning, providing category names or textual descriptions to Vision-Language Models.
Ranked #6 on
Open Vocabulary Object Detection
on LVIS v1.0
(using extra training data)
Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control
While existing character image animation methods using pose sequences and reference images have shown promising performance, they tend to struggle with incoherent animation in complex scenarios, such as multiple character animation and body occlusion.
A Survey of Generative Techniques for Spatial-Temporal Data Mining
By integrating generative techniques and providing a standardized framework, the paper contributes to advancing the field and encourages researchers to explore the vast potential of generative techniques in spatial-temporal data mining.
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
(1) Mutually-Refined Proposal Extraction.
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications.
BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models
However, general LLMs, which are developed on open-domain data, may lack the domain-specific knowledge essential for tasks in vertical domains, such as legal, medical, etc.
DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment
Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and calculate relevance using textual semantic similarity.
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined.
Towards 3D Molecule-Text Interpretation in Language Models
Through 3D molecule-text alignment and 3D molecule-centric instruction tuning, 3D-MoLM establishes an integration of 3D molecular encoder and LM.
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.
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks.
Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images.
LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps).
Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months.
DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query
In DeLR, the query is based on region-level, and we only annotate the object region that is queried; 2) Instead of directly providing both localization and recognition annotations, we separately query the two components, and thus reduce the recognition budget with the pseudo class labels provided by the model.
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
Instead of dismissing the role of incremental learning, we attribute the lack of anticipated performance enhancement to a mismatch between the LLM4Rec architecture and incremental learning: LLM4Rec employs a single adaptation module for learning recommendations, limiting its ability to simultaneously capture long-term and short-term user preferences in the incremental learning context.
When Parameter-efficient Tuning Meets General-purpose Vision-language Models
Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications.
Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views
However, due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views, especially for complex objects.
Boosting Segment Anything Model Towards Open-Vocabulary Learning
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting.
Segment Any 3D Gaussians
This is achieved by attaching an scale-gated affinity feature to each 3D Gaussian to endow it a new property towards multi-granularity segmentation.
Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of large foundation models in novel scenarios with limited training data.
GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians.
One-bit Supervision for Image Classification: Problem, Solution, and Beyond
An intriguing property of the setting is that the burden of annotation largely alleviates in comparison to offering the accurate label.
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions
During reasoning, for leaf nodes, LLMs choose a more confident answer from Closed-book QA that employs parametric knowledge and Open-book QA that employs retrieved external knowledge, thus eliminating the negative retrieval problem.
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks.
AiluRus: A Scalable ViT Framework for Dense Prediction
Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence.
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Representing and rendering dynamic scenes has been an important but challenging task.
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
In recent times, the generation of 3D assets from text prompts has shown impressive results.
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Recently years have witnessed a rapid development of large language models (LLMs).
Computation-efficient Deep Learning for Computer Vision: A Survey
Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks.
A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations.
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
Based on the STA score, we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training.
SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I).
Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion
In this work, we propose a novel strategy named \textbf{Degeneration-Tuning (DT)} to shield contents of unwanted concepts from SD weights.
Human Motion Generation: A Survey
In this survey, we present a comprehensive literature review of human motion generation, which, to the best of our knowledge, is the first of its kind in this field.
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model.
Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models
In this paper, we start with a conceptual definition of AGI and briefly review how NLP solves a wide range of tasks via a chat system.
Exploring Effective Mask Sampling Modeling for Neural Image Compression
Specifically, Cube Mask Sampling Module (CMSM) is proposed to apply both spatial and channel mask sampling modeling to image compression in the pre-training stage.
Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems
To achieve joint channel estimation and feedback, this paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix.
Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT).
ControlVideo: Training-free Controllable Text-to-Video Generation
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling.
Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation
Incremental few-shot semantic segmentation (IFSS) aims to incrementally extend a semantic segmentation model to novel classes according to only a few pixel-level annotated data, while preserving its segmentation capability on previously learned base categories.
Continual Vision-Language Representation Learning with Off-Diagonal Information
Moreover, we empirically and theoretically demonstrate how SD leads to a performance decline for CLIP on cross-modal retrieval tasks.
Visual Tuning
With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer.
Segment Anything in 3D with Radiance Fields
The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results.
SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval
Moreover, in contrast to the general retrieval, the relevance in the legal domain is sensitive to key legal elements.
Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism
The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference.
Learning Transferable Pedestrian Representation from Multimodal Information Supervision
Recent researches on unsupervised person re-identification~(reID) have demonstrated that pre-training on unlabeled person images achieves superior performance on downstream reID tasks than pre-training on ImageNet.
PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
In this work, we propose a ladder self-attention block with multiple branches and a progressive shift mechanism to develop a light-weight transformer backbone that requires less computing resources (e. g. a relatively small number of parameters and FLOPs), termed Progressive Shift Ladder Transformer (PSLT).
Multi-modal Prompting for Low-Shot Temporal Action Localization
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos, even not seen at training time.
LION: Implicit Vision Prompt Tuning
Despite recent competitive performance across a range of vision tasks, vision Transformers still have an issue of heavy computational costs.
Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation
Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the labeled images in the source domain, and (ii) adapting to the target domain via generating pseudo labels on the unlabeled images.
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
Seed area generation is usually the starting point of weakly supervised semantic segmentation (WSSS).
Multi-Label Classification
Weakly supervised Semantic Segmentation
+1
Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models
Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen pre-training models.
Rethinking Visual Prompt Learning as Masked Visual Token Modeling
To explore prompt learning on the generative pre-trained visual model, as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction.
M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i. e., not seen during training), they always predict them as one of the training classes.
Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding
To better accelerate the generative transformers while keeping good generation quality, we propose Lformer, a semi-autoregressive text-to-image generation model.
Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos.
ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories
In this paper, we propose a novel and flexible conditional diffusion model by introducing conditions into the forward process.
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator
PLEor could leverage pre-trained CLIP model to infer the discrepancies encompassing both pre-defined and unknown subcategories, called category-specific discrepancies, and transfer them to the backbone network trained in the close-set scenarios.
Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition
To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation.
Federated Domain Generalization With Generalization Adjustment
Federated Domain Generalization (FedDG) attempts to learn a global model in a privacy-preserving manner that generalizes well to new clients possibly with domain shift.
Prototype-guided Cross-task Knowledge Distillation for Large-scale Models
Considering the complexity and variability of real scene tasks, we propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
And as a result, the dual-branch complementarity is effectively fused to promote a strong alliance.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions.
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.
ConfounderGAN: Protecting Image Data Privacy with Causal Confounder
The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet.
Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning
e. g., an agent is a random policy while other agents are medium policies.
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).
Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast
In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast.
Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion.
End-to-End Context-Aided Unicity Matching for Person Re-identification
Based on a natural assumption that images belonging to the same person identity should not match with images belonging to multiple different person identities across views, called the unicity of person matching on the identity level, we propose an end-to-end person unicity matching architecture for learning and refining the person matching relations.
See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
The issue of image haze removal has attracted wide attention in recent years.
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
Towards this goal, we propose a framework with a unified view of PETL called visual-PETL (V-PETL) to investigate the effects of different PETL techniques, data scales of downstream domains, positions of trainable parameters, and other aspects affecting the trade-off.
Motion-inductive Self-supervised Object Discovery in Videos
In this paper, we consider the task of unsupervised object discovery in videos.
Ranked #3 on
Unsupervised Object Segmentation
on DAVIS 2016
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.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Low-Light Video Enhancement with Synthetic Event Guidance
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving.
Prompt-Matched Semantic Segmentation
Previous methods usually fine-tuned the entire networks for each specific dataset, which will be burdensome to store massive parameters of these networks.
Fine-Grained Semantically Aligned Vision-Language Pre-Training
Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks.
Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles.
SdAE: Self-distillated Masked Autoencoder
We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.
Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands.
Fine-grained Retrieval Prompt Tuning
In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation.
Visual Recognition by Request
Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal.
Pro-tuning: Unified Prompt Tuning for Vision Tasks
To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
Active Pointly-Supervised Instance Segmentation
In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object.
Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
Second, most previous weakly supervised REG methods ignore the discriminative location and context of the referent, causing difficulties in distinguishing the target from other same-category objects.
A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Next, we summarize the existing label-efficient image segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction -- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, and cross-image relation.
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
Inspired by the observation that humans learn to recognize the texts through both reading and writing, we propose to learn discrimination and generation by integrating contrastive learning and masked image modeling in our self-supervised method.
Towards Generalizable Person Re-identification with a Bi-stream Generative Model
Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors.
Domain Generalization
Generalizable Person Re-identification
Masked Autoencoders are Robust Data Augmentors
Specifically, MRA consistently enhances the performance on supervised, semi-supervised as well as few-shot classification.
DE-Net: Dynamic Text-guided Image Editing Adversarial Networks
To solve these limitations, we propose: (i) a Dynamic Editing Block (DEBlock) which composes different editing modules dynamically for various editing requirements.
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.
Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions.
HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval
It also achieves about +4. 9 AR on COCO and +3. 8 AR on Flickr30K than LightingDot and achieves comparable performance with the state-of-the-art (SOTA) fusion-based model METER.
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation
Subject to the huge semantic gap between natural and formal languages, neural semantic parsing is typically bottlenecked by its complexity of dealing with both input semantics and output syntax.
CenterNet++ for Object Detection
Our approach, named CenterNet, detects each object as a triplet keypoints (top-left and bottom-right corners and the center keypoint).
Ranked #36 on
Object Detection
on COCO test-dev
HyperDet3D: Learning a Scene-conditioned 3D Object Detector
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects.
Domain-Agnostic Prior for Transfer Semantic Segmentation
Unsupervised domain adaptation (UDA) is an important topic in the computer vision community.
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers
The past year has witnessed a rapid development of masked image modeling (MIM).
DATA: Domain-Aware and Task-Aware Self-supervised Learning
However, due to the high training costs and the unconsciousness of downstream usages, most self-supervised learning methods lack the capability to correspond to the diversities of downstream scenarios, as there are various data domains, different vision tasks and latency constraints on models.
Deep Class Incremental Learning from Decentralized Data
In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories.
TAPE: Task-Agnostic Prior Embedding for Image Restoration
In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer.
MVP: Multimodality-guided Visual Pre-training
Recently, masked image modeling (MIM) has become a promising direction for visual pre-training.
The KFIoU Loss for Rotated Object Detection
This is in contrast to recent Gaussian modeling based rotation detectors e. g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors.
GhostNets on Heterogeneous Devices via Cheap Operations
The proposed C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks.
One-Bit Active Query With Contrastive Pairs
The Yes query is treated as positive pairs of the queried category for contrastive pulling, while the No query is treated as hard negative pairs for contrastive repelling.
DeeCap: Dynamic Early Exiting for Efficient Image Captioning
On one hand, the representation in shallow layers lacks high-level semantic and sufficient cross-modal fusion information for accurate prediction.
Partial Class Activation Attention for Semantic Segmentation
Current attention-based methods for semantic segmentation mainly model pixel relation through pairwise affinity and coarse segmentation.
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks
Audio-Guided video semantic segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from background in a video sequence according to the referring audio expressions.
Contextual Similarity Distillation for Asymmetric Image Retrieval
To this end, we propose a flexible contextual similarity distillation framework to enhance the small query model and keep its output feature compatible with that of large gallery model, which is crucial with asymmetric retrieval.
Learning To Learn by Jointly Optimizing Neural Architecture and Weights
Existing NAS-based meta-learning methods apply a two-stage strategy, i. e., first searching architectures and then re-training meta-weights on the searched architecture.
CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning
The node information compression aims to address the problem of what to communicate via learning compact node representations.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
General Greedy De-bias Learning
Existing de-bias learning frameworks try to capture specific dataset bias by annotations but they fail to handle complicated OOD scenarios.
SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders.
Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection
In the second stage, augmented source and target data with pseudo labels are adopted to perform the self-training for prediction consistency.
Mining Minority-class Examples With Uncertainty Estimates
In the real world, the frequency of occurrence of objects is naturally skewed forming long-tail class distributions, which results in poor performance on the statistically rare classes.
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}.
NeuSample: Neural Sample Field for Efficient View Synthesis
Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is still heavy.
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
Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes
Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training.
Ranked #10 on
Anomaly Detection
on Fishyscapes L&F
Self-Regulated Learning for Egocentric Video Activity Anticipation
Future activity anticipation is a challenging problem in egocentric vision.
DVCFlow: Modeling Information Flow Towards Human-like Video Captioning
Dense video captioning (DVC) aims to generate multi-sentence descriptions to elucidate the multiple events in the video, which is challenging and demands visual consistency, discoursal coherence, and linguistic diversity.
DocScanner: Robust Document Image Rectification with Progressive Learning
The iterative refinements make DocScanner converge to a robust and superior rectification performance, while the lightweight recurrent architecture ensures the running efficiency.
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses.
Ranked #1 on
3D-Aware Image Synthesis
on FFHQ 256 x 256
Semi-Autoregressive Image Captioning
Non-autoregressive image captioning with continuous iterative refinement, which eliminates the sequential dependence in a sentence generation, can achieve comparable performance to the autoregressive counterparts with a considerable acceleration.
Vibration-based Uncertainty Estimation for Learning from Limited Supervision
We investigate the problem of estimating uncertainty for training data, so that deep neural networks can make use of the results for learning from limited supervision.
Deep Encryption: Protecting Pre-Trained Neural Networks with Confusion Neurons
Having consumed huge amounts of training data and computational resource, large-scale pre-trained models are often considered key assets of AI service providers.
Self-supervised Tumor Segmentation through Layer Decomposition
In this paper, we target self-supervised representation learning for zero-shot tumor segmentation.
Differentiable Convolution Search for Point Cloud Processing
It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling.
Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the relations in motions at various spatial and temporal scales.
Pixel Difference Networks for Efficient Edge Detection
A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
Ranked #2 on
Edge Detection
on BRIND
Greedy Gradient Ensemble for Robust Visual Question Answering
Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information.
Ranked #2 on
Visual Question Answering (VQA)
on VQA-CP
Revisiting Catastrophic Forgetting in Class Incremental Learning
After investigating existing strategies, we observe that there is a lack of study on how to prevent the inter-phase confusion.
Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification
The key to this task is to exploit cloth-irrelevant cues.
Domain Adaptation without Model Transferring
Existing unsupervised domain adaptation (UDA) methods can achieve promising performance without transferring data from source domain to target domain.
Rectifying the Shortcut Learning of Background for Few-Shot Learning
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL).
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.
Bag of Instances Aggregation Boosts Self-supervised Distillation
Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.
ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Image Segmentation
Semi-supervised learning is a useful tool for image segmentation, mainly due to its ability in extracting knowledge from unlabeled data to assist learning from labeled data.