Source-Free Domain Adaptation with Vision-Language Prior proposes DIFO++, a two-step adaptation framework that customizes a vision‑language model (e.g., CLIP) to a target domain via prompt learning and then distills its knowledge into a target model. The method focuses on a gap region where features are entangled and class‑ambiguous, generating reliable pseudo‑labels by fusing predictions from both models and employing memory, category attention, predictive consistency, and entropy minimization to align semantics. Experiments demonstrate that DIFO++ outperforms existing state‑of‑the‑art approaches.
By Song Tang, Yunxiang Bai, Wenxin Su, Mao Ye, Jianwei Zhang, Xiatian Zhu
The paper introduces SubTTA, a test-time adaptation method for vision‑language models that aligns the semantic subspaces of visual and textual modalities to improve zero‑shot predictions. It addresses two issues: the modality gap caused by distribution shifts and visual nuisance that masks task‑specific semantics. By minimizing chordal distance between principal subspaces and projecting visual features onto a task‑specific textual subspace, SubTTA refines decision boundaries and achieves an average 2.24% improvement over existing TTA methods.
By Zhichen Zeng, Wenxuan Bao, Xiao Lin, Ruizhong Qiu, Tianxin Wei, Xuying Ning, Yuchen Yan, Chen Luo, Monica Xiao Cheng, Jingrui He, Hanghang Tong
arXiv:2506.04713v4 Announce Type: replace
Abstract: A key challenge in Few-Shot Recognition (FSR) is the scarcity of labeled task-specific data for training. Contemporary methods mitigate this challe...
By Hanxin Wang, Tian Liu, Shu Kong
The paper explores training a large language model solely on textual video descriptions to perform zero‑shot video temporal localization, eliminating the need for paired video‑text data during training. Using a 134K‑example corpus and adapting Qwen3‑8B with LoRA on CLIP or LLM2CLIP embeddings, the authors evaluate on Charades‑STA and QV‑Highlights, achieving modest performance when directly replacing text with frame embeddings. They introduce Nearest Entity Replacement (NER), a training‑free mapping that represents each video frame by the mean of its nearest text‑entity embeddings, which significantly improves results and narrows the modality gap.
By Divyanshu Mishra, Sabine Sternig, Rakshith Shetty, Erhan Gundogdu
arXiv:2410.21582v4 Announce Type: replace-cross
Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of mainta...
By Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
arXiv:2609.10321v1 Announce Type: new
Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...
By Hongyuan Zhang, Xianda Guo, Yanlun Peng, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, Ping Luo
arXiv:2505.07675v3 Announce Type: replace-cross
Abstract: Semi-supervised learning (SSL) has emerged as a practical solution for addressing data scarcity challenges by leveraging unlabeled data. Rece...
By Seongjae Kang, Dong Bok Lee, Hyungjoon Jang, Sung Ju Hwang
arXiv:2609.24564v1 Announce Type: new
Abstract: CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encode...
By Zelin Peng, Zhengqin Xu, Changsong Wen, Yu Huang, Yaoming Wang, Xiaokang Yang, Wei Shen
LinMorph proposes a learnable softmax‑to‑linear weight transformation for Video Diffusion Transformers, replacing traditional random initialization or manual weight reuse. By learning a shared morphism that maps each target Gated DeltaNet parameter to a combination of pretrained query, key, value, and output projections, it generates layer‑specific initializations that preserve pretrained knowledge. The method enables faster recovery and higher generation quality across pretrained Video DiTs, especially when applied to larger video scales after training on short, low‑resolution clips.
By Lingyi Long, Congyue Zhao, Xiaoou Li, Yanmin Qian, Tao Huang
The paper introduces Adaptive Dual-Teacher Distillation with Subnetwork Rectification (DDSR), a method for black-box domain adaptation that fuses predictions from a black-box source model and a vision‑language model to generate reliable pseudo‑labels for the target domain. DDSR uses adaptive prediction fusion, subnetwork regularization to prevent overfitting, iterative refinement of pseudo‑labels and prompts, and class‑wise prototypes for self‑training. Experiments on several benchmark datasets show that DDSR outperforms existing state‑of‑the‑art approaches, even those that have access to source data or source model parameters.
By Zhe Zhang, Jing Li, Wanli Xue, Xu Cheng, Jianhua Zhang, Qinghua Hu, Shengyong Chen
SD‑LoRA introduces a training‑time structural distillation framework that embeds token‑level graph reasoning into a lightweight LoRA‑adapted CLIP model for few‑shot vision‑language adaptation. During training, a heterogeneous graph teacher captures patch‑patch, global‑local, and visual‑text relations over high‑resolution ViT tokens, and its structural bias is transferred to the CLIP‑LoRA backbone via implicit distillation and Prototype Predictive Alignment. At inference, the graph teacher is discarded, requiring only a single CLIP‑LoRA forward pass and a cache‑based classifier, yielding significant accuracy gains across 11 few‑shot benchmarks without extra computation.
By Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan, Swagat Kumar, Yonghuai Liu
arXiv:2607. 00858v1 Announce Type: cross Abstract: Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled representations.
By Peiyuan Zhu, Shaoan Xie, Zijian Li, Yifan Shen, Namrata Deka, Harsh Shrivastava, Guangyi Chen, Kun Zhang