Search Results for author:
Found 15 papers, 9 papers with code
Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
In this paper, we propose a dynamic object-centric perception network based on prompt learning, aiming to adapt to the variations in image complexity.
Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation
Then, we construct a class-balanced curriculum learning strategy to balance the different environments to remove the predicate imbalance.
Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects
For this task, the challenge mainly lies in how to only leverage the known in-distribution (ID) data to detect OOD objects accurately without affecting the detection of ID objects, which can be framed as the diffusion problem for deep feature synthesis.
Discriminating Known From Unknown Objects via Structure-Enhanced Recurrent Variational AutoEncoder
To simulate this ability, a task of unsupervised out-of-distribution object detection (OOD-OD) is proposed to detect the objects that are never-seen-before during model training, which is beneficial for promoting the safe deployment of object detectors.
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.
Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation
Particularly, for the night-sunny scene, our method outperforms baselines by 3%, which indicates that our method is instrumental in enhancing generalization ability.
Ranked #3 on
Robust Object Detection
on DWD
Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery
In response to the explosively-increasing requirement of annotated data, Novel Class Discovery (NCD) has emerged as a promising alternative to automatically recognize unknown classes without any annotation.
Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement
To alleviate the impact of few samples, enhancing the generalization and discrimination abilities of detectors on new objects plays an important role.
Vector-Decomposed Disentanglement for Domain-Invariant Object Detection
Secondly, domain-specific representations are introduced as the differences between the input and domain-invariant representations.
Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches.
Universal-Prototype Enhancing for Few-Shot Object Detection
Thus, we develop a new framework of few-shot object detection with universal prototypes ({FSOD}^{up}) that owns the merit of feature generalization towards novel objects.
Ranked #23 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Hierarchical memory decoder for visual narrating
In this article, we devise a novel memory decoder for visual narrating.
Ranked #13 on
Visual Storytelling
on VIST
Hierarchical Memory Decoding for Video Captioning
Instead of the common practice, i. e., sequence decoding with RNN, in this paper, we devise a novel memory decoder for video captioning.
Connective Cognition Network for Directional Visual Commonsense Reasoning
Inspired by this idea, towards VCR, we propose a connective cognition network (CCN) to dynamically reorganize the visual neuron connectivity that is contextualized by the meaning of questions and answers.
Instance-Invariant Domain Adaptive Object Detection via Progressive Disentanglement
Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e. g., with different styles.
