finite
发表于 2025-3-30 08:20:39
,Non-exemplar Domain Incremental Learning via Cross-Domain Concept Integration, exemplar-based solutions are not always viable due to data privacy concerns or storage limitations.Therefore, Non-Exemplar Domain Incremental Learning (NEDIL) has emerged as a significant paradigm for resolving DIL challenges.Current NEDIL solutions extend the classifier incrementally for new domai
aplomb
发表于 2025-3-30 13:57:18
,Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression,wever, the semantic richness of previous methods remains limited, due to the single semantic learning objective, limited training data, etc. To address this, we propose to boost the UVSC task by absorbing the off-the-shelf rich semantics from VFMs. Specifically, we introduce a VFMs-shared semantic a
真繁荣
发表于 2025-3-30 18:03:15
,Improving Virtual Try-On with Garment-Focused Diffusion Models, apply diffusion models for synthesizing an image of a target person wearing a given in-shop garment, i.e., image-based virtual try-on (VTON) task. The difficulty originates from the aspect that the diffusion process should not only produce holistically high-fidelity photorealistic image of the targ
Petechiae
发表于 2025-3-30 23:24:31
http://reply.papertrans.cn/25/2424/242333/242333_54.png
Pathogen
发表于 2025-3-31 01:18:39
,Disentangled Generation and Aggregation for Robust Radiance Fields,h a high-quality representation and low computation cost. A key requirement of this method is the precise input of camera poses. However, due to the local update property of the triplane, a similar joint estimation as previous joint pose-NeRF optimization works easily results in local minima. To thi
incite
发表于 2025-3-31 05:01:08
,UNIKD: UNcertainty-Filtered Incremental Knowledge Distillation for Neural Implicit Representation,quire the images of a scene from different camera views to be available for one-time training. This is expensive especially for scenarios with large-scale scenes and limited data storage. In view of this, we explore the task of incremental learning for NIRs in this work. We design a student-teacher
drusen
发表于 2025-3-31 12:29:06
,Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation, segmentation network is influenced by the quantity of samples available for different categories. To mitigate the cognitive bias induced by class imbalance, this paper introduces a novel method, namely subspace prototype guidance (.), to guide the training of segmentation network. Specifically, the
CURL
发表于 2025-3-31 14:03:30
http://reply.papertrans.cn/25/2424/242333/242333_58.png
Orchiectomy
发表于 2025-3-31 17:50:39
,Semantic-Guided Robustness Tuning for Few-Shot Transfer Across Extreme Domain Shift,in shift between base and novel target classes. Current methods always employ a lightweight backbone and continue to use a linear-probe-like traditional fine-tuning (Trad-FT) paradigm. While for recently emerging large-scale pre-trained model (LPM), which has more parameters with considerable prior
后来
发表于 2025-4-1 01:19:01
,Revisit Event Generation Model: Self-supervised Learning of Event-to-Video Reconstruction with Implvent-based and frame-based computer vision. Previous approaches have depended on supervised learning on synthetic data, which lacks interpretability and risk over-fitting to the setting of the event simulator. Recently, self-supervised learning (SSL) based methods, which primarily utilize per-frame