The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nam, Kahyeon, Choi, Hyesong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Amortized-Precision Quantization for Early-Exit Vision Transformers
by: Fang, Rui, et al.
Published: (2026)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
by: Kim, Jiyeong, et al.
Published: (2026)

SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exit
by: Hu, Youbing, et al.
Published: (2025)

When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
by: Kim, Jihyeon, et al.
Published: (2026)

Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization
by: Khan, Anas Anwarul Haq, et al.
Published: (2025)

CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
by: Zhou, Qiongyi, et al.
Published: (2024)

Unleash the Potential of CLIP for Video Highlight Detection
by: Han, Donghoon, et al.
Published: (2024)

DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
by: Choraria, Moulik, et al.
Published: (2025)

CLIP-Guided Unsupervised Semantic-Aware Exposure Correction
by: Wu, Puzhen, et al.
Published: (2026)

E4: Energy-Efficient DNN Inference for Edge Video Analytics Via Early-Exit and DVFS
by: Zhang, Ziyang, et al.
Published: (2025)

Knowledge-Base based Semantic Image Transmission Using CLIP
by: Li, Chongyang, et al.
Published: (2025)

Learning Context-Conditioned Predicate Semantics via Prototype Feedback
by: Jung, NamGyu, et al.
Published: (2026)

Mitigating Semantic Collapse in Partially Relevant Video Retrieval
by: Moon, WonJun, et al.
Published: (2025)

Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation
by: Stangl, Kevin, et al.
Published: (2024)

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
by: Yang, Shengzhu, et al.
Published: (2025)

SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones
by: Khazem, Salim
Published: (2026)

CLIP is All You Need for Human-like Semantic Representations in Stable Diffusion
by: Braunstein, Cameron, et al.
Published: (2025)

Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning
by: Yu, Jiaao, et al.
Published: (2025)

Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions
by: Taghipour, Ashkan, et al.
Published: (2024)

ViFusionTST: Deep Fusion of Time-Series Image Representations from Load Signals for Early Bed-Exit Prediction
by: Liu, Hao, et al.
Published: (2025)

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
by: Lee, Sangin, et al.
Published: (2026)

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization
by: Wang, Xinghao, et al.
Published: (2026)

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
by: Xun, Yuan, et al.
Published: (2024)

Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation
by: Dalaq, Alaa, et al.
Published: (2026)

PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization
by: Lahiany, Assaf, et al.
Published: (2025)

Enhancing Generalization in Data-free Quantization via Mixup-class Prompting
by: Park, Jiwoong, et al.
Published: (2025)

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
by: Gao, Bin-Bin, et al.
Published: (2025)

DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding
by: Wang, Zhu, et al.
Published: (2025)

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation
by: Lee, ByeongCheol, et al.
Published: (2026)

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP
by: Cai, Yuliang, et al.
Published: (2025)

SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models
by: Zhang, Jiaji, et al.
Published: (2025)

MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
by: Li, Juan, et al.
Published: (2026)

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
by: Zhang, Jihai, et al.
Published: (2024)

AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP
by: Ma, Wenxin, et al.
Published: (2025)

CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP
by: Zeng, Yirui, et al.
Published: (2025)

FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection
by: Chen, Yulin, et al.
Published: (2025)

DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
by: HU, Haibo, et al.
Published: (2025)

Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding
by: Xu, Jingqi
Published: (2026)

No Captions, No Problem: Captionless 3D-CLIP Alignment with Hard Negatives via CLIP Knowledge and LLMs
by: Sbrolli, Cristian, et al.
Published: (2024)