Search Results for author:
Found 29 papers, 12 papers with code
Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis.
CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
We present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i. e., rendered from the canonical content field) to each individual frame along the time axis. Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline. We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e. g., the object shape) from the video. With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field. We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training. More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog. Project page can be found at https://qiuyu96. github. io/CoDeF/.
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen.
Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase
Despite the rapid advance of 3D-aware image synthesis, existing studies usually adopt a mixture of techniques and tricks, leaving it unclear how each part contributes to the final performance in terms of generality.
Cones 2: Customizable Image Synthesis with Multiple Subjects
Synthesizing images with user-specified subjects has received growing attention due to its practical applications.
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set.
Cones: Concept Neurons in Diffusion Models for Customized Generation
Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.
Neural Dependencies Emerging from Learning Massive Categories
Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others.
Rank Diminishing in Deep Neural Networks
By virtue of our numerical tools, we provide the first empirical analysis of the per-layer behavior of network rank in practical settings, i. e., ResNets, deep MLPs, and Transformers on ImageNet.
Principled Knowledge Extrapolation with GANs
Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions.
FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization
However, its generalization performance to heterogeneous tasks is inferior to other architectures (e. g., CNNs and transformers) due to the extensive retention of domain information.
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Generalizable Person Re-identification
Representation Learning
Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images.
Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification
Image-to-video person re-identification aims to retrieve the same pedestrian as the image-based query from a video-based gallery set.
Image-To-Video Person Re-Identification
reinforcement-learning
+4
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
Calibrated Feature Decomposition for Generalizable Person Re-Identification
The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.
Domain Generalization
Generalizable Person Re-identification
Semi-Supervised Domain Generalizable Person Re-Identification
Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.
Ranked #16 on
Person Re-Identification
on Market-1501
(using extra training data)
Generalizable Person Re-identification
Knowledge Distillation
+1
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Occluded person re-identification (ReID) aims to match person images with occlusion.
Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification
It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline.
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video sequences.
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.
Ranked #5 on
Person Re-Identification
on PRCC
Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
The cross-modal memory module is employed to record the instance embeddings of all the datasets for global negative mining.
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.
Group-aware Label Transfer for Domain Adaptive Person Re-identification
In this paper, we propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning.
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss.
Hierarchical Gumbel Attention Network for Text-based Person Search
This hard selection strategy is able to fuse the strong-relevant multi-modality features for alleviating the problem of matching redundancy.
Ranked #13 on
Text based Person Retrieval
on CUHK-PEDES
Stacked Convolutional Deep Encoding Network for Video-Text Retrieval
Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity.
Abstract Reasoning with Distracting Features
Abstraction reasoning is a long-standing challenge in artificial intelligence.
